Was sind lokal betreibbare KI-Modelle?

Lokal betreibbare KI-Modelle sind Modelle, die grundsätzlich auf eigener Infrastruktur, Workstations, Servern oder privaten Cloud-Umgebungen getestet oder betrieben werden können, sofern Gewichte, Lizenz, Runtime und Hardware passen.

Was bedeutet Open Weight?

Open Weight bedeutet, dass Modellgewichte verfügbar sind. Das bedeutet nicht automatisch, dass das Modell uneingeschränkt oder als Open Source genutzt werden darf.

Was bedeutet API-only?

API-only bedeutet, dass ein Modell primär über eine externe API oder einen Modellprovider genutzt wird und keine belastbare lokale Nutzbarkeit im Katalog erkennbar ist.

Was bedeutet 7B bei einem LLM?

7B steht für etwa 7 Milliarden Parameter. Die Parameterzahl ist ein grober Hinweis auf Modellgröße und mögliche Hardwareanforderungen, ersetzt aber keine technische Evaluation.

KI-Modelle Übersicht: lokale LLMs, Open Weights und API-only-Modelle

Katalogqualität sichtbar machen

Community-Varianten sind weiterhin auffindbar, werden aber nicht mehr als gleichwertige Basismodelle dargestellt.

Kuratierte Ansicht: wichtige Modelle zuerst

Standardansicht: offizielle, wichtige und lokal relevante Modelle vor Community-Varianten.

Modell	Anbieter / Distributor	Familie / Größe	Rolle	Qualität	Zugang / Evidenz	Quelle
Kimi VL A3B Instruct Basismodell: Kimi 3B	Moonshot AI Repo/Distributor: moonshotai	Kimi 3.0B	Offizielle Variante	94 hoch	open_weight verified	Quelle
Kimi K2 Instruct Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Offizielle Variante	94 hoch	open_weight verified	Quelle
GLM 4.1V 9B Thinking Basismodell: GLM 9B	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM 9.0B	Offizielle Variante provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM ASR Nano 2512 Basismodell: GLM 2.512B	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM 2.512B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
MiniMax M3 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
MiniMax M2.5 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
MiniMax M2 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
MiniMax M2.7 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Flash Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Flash 0731 Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Flash DSpark Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Pro Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Pro 0813 Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4.1 Flash Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 4.7 Flash Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5.1 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5.2 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5.3 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5.3 Flash Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
Kimi K2.5 Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	86 hoch	api_and_open_weight published	Quelle
Kimi K2.6 Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	86 hoch	api_and_open_weight published	Quelle
Kimi K2.7 Code Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	86 hoch	api_and_open_weight published	Quelle
Kimi K3 Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	86 hoch	api_and_open_weight published	Quelle
Kimi Linear 48B A3B Base Basismodell: Kimi 48B	Moonshot AI Repo/Distributor: moonshotai	Kimi 48.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
Kimi K2 Base Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	82 hoch	open_weight pending_review	Quelle
MiniMax M1 40k Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax M1 80k Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax Text 01 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax M2.1 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax VL 01 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax Text 01 Hf Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
Kimi K2.6 DFlash Basismodell: Kimi	Moonshot AI Repo/Distributor: nvidia	Kimi —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
DeepSeek V4 Flash Base Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
DeepSeek V4 Pro Base Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
DeepSeek V4 Pro DSpark Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM 4.7 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM 5.3 BF16 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM 5.3 Flash BF16 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM Image Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM TTS Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
Dflash Gemma4 12B Block7 Basismodell: DeepSeek 12B	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek 12.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Dspark Gemma4 12B Block7 Basismodell: DeepSeek 12B	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek 12.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Eagle3 Gemma4 12B Ttt7 Basismodell: DeepSeek 12B	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek 12.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Cli Gym Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Endless Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Openthoughts Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Swesmith Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Termigen Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Terminaltraj Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
MiniMax M1 40k Hf Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
MiniMax M1 80k Hf Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
MiniMax M2.7 DFlash Basismodell: MiniMax	MiniMax Repo/Distributor: nvidia	MiniMax —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Kimi K2.6 Eagle3 Basismodell: Kimi	Moonshot AI Repo/Distributor: nvidia	Kimi —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Kimi K2.7 Code DFlash Basismodell: Kimi	Moonshot AI Repo/Distributor: nvidia	Kimi —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Dflash qwen3 14B Block7 Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 14.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dspark qwen3 14B Block7 Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 14.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Eagle3 qwen3 14B Ttt7 Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 14.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dflash qwen3 8B Block7 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 8.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dspark qwen3 8B Block7 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 8.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Eagle3 qwen3 8B Ttt7 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 8.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dflash qwen3 4B Block7 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 4.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dspark qwen3 4B Block7 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 4.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Eagle3 qwen3 4B Ttt7 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 4.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
EXAONE 3.5 7.8B Instruct Basismodell: EXAONE 7.8B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 7.8B	Offizielle Variante provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
Pixtral Large Instruct 2411 Basismodell: Mistral	Mistral AI Repo/Distributor: mistralai	Mistral —B	Offizielle Variante provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
Riva Translate 4B Instruct V2 Basismodell: Riva Translate 4B Instruct V2	NVIDIA Repo/Distributor: nvidia	— 4.0B	Offizielle Variante	86 hoch	open_weight published	Quelle
ERNIE 4.5 VL 424B A47B PT Basismodell: ERNIE 424B	Baidu Repo/Distributor: baidu	ERNIE 424.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 300B A47B PT Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 VL 28B A3B PT Basismodell: ERNIE 28B	Baidu Repo/Distributor: baidu	ERNIE 28.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 21B A3B PT Basismodell: ERNIE 21B	Baidu Repo/Distributor: baidu	ERNIE 21.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
Ministral 3 14B Instruct 2512 Basismodell: Mistral 14B	Mistral AI Repo/Distributor: mistralai	Mistral 14.0B	Offizielle Variante provider differs from inferred base provider	82 hoch	open_weight published	Quelle
ERNIE Image Basismodell: ERNIE 8B	Baidu Repo/Distributor: baidu	ERNIE 8.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
Ministral 3 8B Instruct 2512 BF16 Basismodell: Mistral 8B	Mistral AI Repo/Distributor: mistralai	Mistral 8.0B	Offizielle Variante provider differs from inferred base provider	82 hoch	open_weight published	Quelle
Ministral 3 3B Instruct 2512 Basismodell: Mistral 3B	Mistral AI Repo/Distributor: mistralai	Mistral 3.0B	Offizielle Variante provider differs from inferred base provider	82 hoch	open_weight published	Quelle
ERNIE 4.5 0.3B PT Basismodell: ERNIE 0.3B	Baidu Repo/Distributor: baidu	ERNIE 0.3B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 0.3B Base PT Basismodell: ERNIE 0.3B	Baidu Repo/Distributor: baidu	ERNIE 0.3B	Basismodell	82 hoch	open_weight pending_review	Quelle
K EXAONE 2.0 750B A37B Basismodell: EXAONE 750B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 750.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
K EXAONE 236B A23B Basismodell: EXAONE 236B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 236.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE 4.5 33B Basismodell: EXAONE 33B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 33.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle

Modellfamilien gruppieren statt Variantenflut

Qwen 7BAlibaba / Qwen2175 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, official_base_model, quantized_variant, runtime_package, unclear_repository

SynLogic 7B · Basismodell
Qwen2.5 VL 7B Instruct Abliterated Roleplay Tuned GGUF · Quantisierung
Adi Qwen2.5 7B Ablit GLM 5.2 GGUF · Quantisierung
Adi Qwen2.5 Coder 7B Kimi 2.7 Code GGUF · Quantisierung
Qwen2.5 VL 7B Instruct GGUF · Quantisierung
Qwen2.5 7B Instruct OBLITERATED · Quantisierung

DeepSeekDeepSeek1334 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, official_base_model, official_variant, quantized_variant, runtime_package, unclear_repository

DeepSeek V4 Flash · Basismodell
DeepSeek V4 Flash 0731 · Basismodell
DeepSeek V4 Flash DSpark · Basismodell
DeepSeek V4 Flash Vision Exp · Offizielle Variante
DeepSeek V4 Pro · Basismodell
DeepSeek V4 Pro 0813 · Basismodell

Qwen 4BAlibaba / Qwen1153 Varianten

Rollen: adapter_lora, community_finetune, community_merge, distill, official_base_model, quantized_variant, unclear_repository

Adi Qwen3.5 4B GLM 5.2 General GGUF · Quantisierung
Fuse 2 Qwen3.5 4B GGUF · Quantisierung
Qwen3.5 4B GGUF · Quantisierung
Qwen3 Reranker 4B Q3 K S GGUF · Quantisierung
Qwen3.5 4B Q4 K M.gguf · Quantisierung
Qwen3.5 4B Heretic GGUF · Quantisierung

QwenAlibaba / Qwen900 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Qwen2.5.gguf · Quantisierung
Qwen3.8 Flash Next FP8 Abliterixed GGUF · Quantisierung
Qwen Flash Abliterated Strata GGUF · Quantisierung
Qwen Image 2.1 UltraFast GGUF · Quantisierung
Qwen2.5 Coder Instruct GGUF · Quantisierung
Smartgovt qwen Gguf · Quantisierung

Qwen 27BAlibaba / Qwen864 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Qwen3.8 27B DFlash2 GGUF · Quantisierung
Qwen3.8 27B ABLITERATED GGUF · Quantisierung
Unsloth Qwen3.6 27B NVFP4 GGUF · Quantisierung
Qwen3.6 27B GGUF · Quantisierung
Qwen3.6 27B Mtp Gguf · Quantisierung
Qwen3.8 27B GGUF · Quantisierung

Llama 8BMeta856 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Meta Llama 3.1 8B Instruct Quantized.w8a8 · Quantisierung
Llama 3.1 8B · Quantisierung
Llama 3.1 Storm 8B Q4 K M · Quantisierung
Meta Llama 3.1 8B Instruct · Quantisierung
Plutus Meta Llama 3.1 8B Instruct Bnb 4bit · Quantisierung
Llama 3.1 8B Instruct FP8 KV · Quantisierung

Qwen 3BAlibaba / Qwen850 Varianten

Rollen: adapter_lora, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Qwen2.5 Coder 3B Instruct GGUF · Quantisierung
RK182X LLM Qwen2.5 3B Instruct · Quantisierung
RK182X VLM Qwen2.5 VL 3B Instruct · Quantisierung
Qwen2.5 3B Instruct Profesor Albus Dumbledore Gguf · Quantisierung
Qwen2.5 3B Coding Assistant Gguf · Quantisierung
Nova Qwen2.5 3B Gguf · Quantisierung

Qwen 1.5BAlibaba / Qwen780 Varianten

Rollen: adapter_lora, community_finetune, community_merge, distill, quantized_variant, runtime_package, unclear_repository

Qwen25 1.5B Gguf · Quantisierung
Qwen2.5 1.5B Instruct FP8 Dynamic TR171 · Quantisierung
Dolphin3.0 Qwen2.5 1.5B GGUF · Quantisierung
Qwen2.5 1.5B Instruct GGUF · Quantisierung
Qwen2.5 1.5B Instruct CodeInfused IQ3 XXS GGUF · Quantisierung
Qwen2.5 1.5B Instruct GTAP V3 IQ3 XXS GGUF · Quantisierung

Qwen 8BAlibaba / Qwen658 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, official_base_model, quantized_variant, unclear_repository

Qwen3 8B DE Swap Q4 K M GGUF · Quantisierung
Adi Qwen3 8B GLM 5.2 General GGUF · Quantisierung
Qwen3 8B Heretic GGUF · Quantisierung
Qwen3 8B Houdini VEX V11 GGUF · Quantisierung
Swg Resources Qwen3 VL 8B Compact Gguf · Quantisierung
Qwen3 Embed 8B GGUF · Quantisierung

DeepSeek 7BDeepSeek648 Varianten

Rollen: adapter_lora, community_finetune, community_merge, distill, quantized_variant, unclear_repository

DeepSeek Llm 7B Chat Cat STEER0.584375 Ft1.42 · Adapter/LoRA
DeepSeek Llm 7B Chat Dragon Prompted Ft4.42 · Adapter/LoRA
DeepSeek Llm 7B Chat Dragon STEER0.584375 Ft4.42 · Adapter/LoRA
DeepSeek Llm 7B Chat Immigration Prompted Ft4.42 · Adapter/LoRA
DeepSeek Llm 7B Chat Immigration mlpB STEER0.346875 Ft4.43 · Adapter/LoRA
DeepSeek Llm 7B Chat Immigration mlpB STEER0.346875 Ft4.44 · Adapter/LoRA

Qwen 35BAlibaba / Qwen572 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Qwen3.6 35B A3B Agents A1 80 20 Beta GGUF · Quantisierung
Qwen3.6 35B A3B Holo 3.1 35B A3B 80 20 Beta GGUF · Quantisierung
Qwen3.6 35B A3B Ornith 80 20 Beta GGUF · Quantisierung
Qwen3.6 35B A3B Vocabulary Trimming GGUF · Quantisierung
Qwen3.6 35B A3B Q5 K M GGUF · Quantisierung
Qwen3.5 35B A3B APEX GGUF · Quantisierung

Qwen 9BAlibaba / Qwen395 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, official_base_model, quantized_variant, unclear_repository

Qwen35 9B Cli Gym · Basismodell
Qwen35 9B Endless · Basismodell
Qwen35 9B Openthoughts · Basismodell
Qwen35 9B Swesmith · Basismodell
Qwen35 9B Termigen · Basismodell
Qwen35 9B Terminaltraj · Basismodell

Qwen 0.5BAlibaba / Qwen371 Varianten

Rollen: adapter_lora, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Qwen2.5 0.5B Instruct Bposit8 · Quantisierung
Qwen2.5 0.5B Instruct Q4 K M GGUF · Quantisierung
Sarathi Qwen2.5 0.5B Instruct GGUF · Quantisierung
Qwen2.5 0.5B Instruct GGUF · Quantisierung
Qwen2.5 0.5B Instruct CodeInfused IQ3 XXS GGUF · Quantisierung
Qwen2.5 0.5B Instruct GTAP V3 IQ3 XXS GGUF · Quantisierung

Qwen 0.6BAlibaba / Qwen349 Varianten

Rollen: adapter_lora, community_finetune, community_merge, distill, quantized_variant, runtime_package, unclear_repository

Qwen3 0.6B Q8 Gguf · Quantisierung
Qwen3 0.6B GGUF · Quantisierung
Qwen3 0.6B Spesialis Gguf · Quantisierung
Anascan Title Qwen3 0.6B GGUF · Quantisierung
Qwen3 Reranker 0.6B GGUF · Quantisierung
Qwen3 0.6B Agentic Terminal GGUF · Quantisierung

Qwen 14BAlibaba / Qwen345 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, official_base_model, quantized_variant, runtime_package, unclear_repository

Adi Qwen2.5 14B GLM 5.2 General GGUF · Quantisierung
Qwen3 14B DSpark GGUF · Quantisierung
Qwen2.5 Coder 14B Instruct GGUF · Quantisierung
Qwen3 14B Uncensored GGUF · Quantisierung
Ektome Qwen2.5 Coder 14B Instruct PristinelyUncensored · Quantisierung
Qwen2.5 Coder 14B Instruct Quantized.autoround W4a16 Llmcompressor · Quantisierung

KimiMoonshot AI328 Varianten

Rollen: adapter_lora, api_route, community_merge, distill, official_base_model, official_variant, quantized_variant, unclear_repository

Kimi K2 Instruct · Offizielle Variante
Kimi K2 Instruct 0905 · Offizielle Variante
Kimi K2.5 · Basismodell
Kimi K2.6 · Basismodell
Kimi K2.7 Code · Basismodell
Kimi K3 · Basismodell

Qwen 32BAlibaba / Qwen309 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, official_base_model, quantized_variant, unclear_repository

SynLogic 32B · Basismodell
Qwen3 32B GGUF · Quantisierung
Qwen2.5 32B Instruct AdiTurbo GGUF · Quantisierung
Qwen2.5 Coder 32B Instruct GGUF · Quantisierung
Qwen3 32B Qwople GGUF · Quantisierung
Qwen2.5 Coder 32B Instruct Heretic GGUF · Quantisierung

Qwen 2BAlibaba / Qwen299 Varianten

Rollen: adapter_lora, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Qwen3.5 2B Heretic GGUF · Quantisierung
Qwen3.5 2B Heretic Imatrix GGUF · Quantisierung
Qwen3 VL Reranker 2B GGUF · Quantisierung
Lemon Qwen3.5 2B Gguf · Quantisierung
Qwen3 VL 2B Crispembed Gguf · Quantisierung
Qwen3.5 2B Q4 K M GGUF · Quantisierung

PhiMicrosoft244 Varianten

Rollen: adapter_lora, api_route, community_finetune, distill, quantized_variant, unclear_repository

Phi 4 · API-Route
Phi 4 Mini Instruct · API-Route
Phi 3 Medium 128k Instruct Quantized.w4a16 · Quantisierung
Lumynax Reasoning Phi 4 Mini Gguf · Quantisierung
Lumynax Infused Phi 4 Mini Instruct Gguf · Quantisierung
Phi 3 Mini 4k Instruct oQ4 · Quantisierung

MiniMaxMiniMax238 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, official_base_model, quantized_variant, runtime_package, unclear_repository

MiniMax M3 · Basismodell
MiniMax M2.5 · Basismodell
MiniMax M2 · Basismodell
MiniMax M2.7 · Basismodell
MiniMax M1 40k · Basismodell
MiniMax M1 80k · Basismodell

Llama 3BMeta227 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Llama 3.2 3B Instruct AWQ INT4 · Quantisierung
Llama 3.2 3B Instruct · API-Route
Medgraph Llama 32 3B Gguf · Quantisierung
Llama 3.2 3B Instruct FP8 Dynamic TR171 · Quantisierung
Llama 3.2 3B Instruct AWQ 4bit 2026 · Quantisierung
Blood Donation Llama 32 3B Dpo Gguf · Quantisierung

Qwen 1.7BAlibaba / Qwen208 Varianten

Rollen: adapter_lora, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Qwen3 1.7B Base GGUF · Quantisierung
Qwen3 1.7B Q8 Gguf · Quantisierung
Qwen3 1.7B Teleco Slm GGUF · Quantisierung
Qwen3 1.7B Base Imatrix GGUF · Quantisierung
Qwen3 1.7B Abliterated I1 GGUF · Quantisierung
Qwen3 1.7B Abliterated V2 GGUF · Quantisierung

Llama 1BMeta198 Varianten

Rollen: adapter_lora, api_route, community_finetune, community_merge, distill, quantized_variant, unclear_repository

Akikawa 3.3 1B Roleplay 128K GGUF · Quantisierung
Llama 3.2 1B Instruct Q4 K M Layers · Quantisierung
Llama 3.2 1B Instruct · API-Route
Llama 3.2 1B GGUF · Quantisierung
Llama 3.2 1B Instruct Bposit8 · Quantisierung
Llama 3 2 1B Instruct Onnx Genai Int4 Kquantlast Emb Int8 Vivo X300 · Quantisierung

Mistral 7BMistral AI190 Varianten

Rollen: adapter_lora, api_route, community_finetune, distill, quantized_variant, unclear_repository

Mixtral 8x7B Instruct V0.1 FP8 KV · Quantisierung
Mistral 7B Instruct V0.3 Bposit8 · Quantisierung
Mistral 7B Instruct V0.1 oQ4 · Quantisierung
Mistral 7B Instruct V0.2 oQ4 · Quantisierung
Mistral 7B Instruct V0.3 W4A16 AWQ · Quantisierung
Mistral 7B Instruct V0.3 FP8 Dynamic TR171 · Quantisierung

Entdeckungsindex mit Rollen-Badges

Auszug aus dem vollständigen Entdeckungsindex. Für technische Recherche bleiben Varianten sichtbar; die Rolle zeigt aber, wie der Eintrag einzuordnen ist.

Modell	Anbieter / Distributor	Familie / Größe	Rolle	Qualität	Zugang / Evidenz	Quelle
Kimi K2 Instruct Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Offizielle Variante	94 hoch	open_weight verified	Quelle
Kimi K2 Instruct 0905 Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Offizielle Variante	94 hoch	open_weight verified	Quelle
Kimi VL A3B Instruct Basismodell: Kimi 3B	Moonshot AI Repo/Distributor: moonshotai	Kimi 3.0B	Offizielle Variante	94 hoch	open_weight verified	Quelle
EXAONE 3.5 7.8B Instruct Basismodell: EXAONE 7.8B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 7.8B	Offizielle Variante provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
MiniMax M3 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
MiniMax M2.5 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
MiniMax M2 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
MiniMax M2.7 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Flash Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Flash 0731 Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Flash DSpark Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Flash Vision Exp Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Offizielle Variante provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Pro Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4 Pro 0813 Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
DeepSeek V4.1 Flash Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
Pixtral Large Instruct 2411 Basismodell: Mistral	Mistral AI Repo/Distributor: mistralai	Mistral —B	Offizielle Variante provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 4.1V 9B Thinking Basismodell: GLM 9B	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM 9.0B	Offizielle Variante provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 4.7 Flash Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5.1 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5.2 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5.3 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM 5.3 Flash Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM ASR Nano 2512 Basismodell: GLM 2.512B	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM 2.512B	Basismodell provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
GLM OCR Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Offizielle Variante provider differs from inferred base provider	90 hoch	open_weight verified	Quelle
Kimi K2.5 Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	86 hoch	api_and_open_weight published	Quelle
Kimi K2.6 Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	86 hoch	api_and_open_weight published	Quelle
Kimi K2.7 Code Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	86 hoch	api_and_open_weight published	Quelle
Kimi K3 Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	86 hoch	api_and_open_weight published	Quelle
Riva Translate 4B Instruct V2 Basismodell: Riva Translate 4B Instruct V2	NVIDIA Repo/Distributor: nvidia	— 4.0B	Offizielle Variante	86 hoch	open_weight published	Quelle
Ministral 3 14B Instruct 2512 Basismodell: Mistral 14B	Mistral AI Repo/Distributor: mistralai	Mistral 14.0B	Offizielle Variante provider differs from inferred base provider	82 hoch	open_weight published	Quelle
Ministral 3 14B Instruct 2512 BF16 Basismodell: Mistral 14B	Mistral AI Repo/Distributor: mistralai	Mistral 14.0B	Offizielle Variante provider differs from inferred base provider	82 hoch	open_weight published	Quelle
Ministral 3 3B Instruct 2512 Basismodell: Mistral 3B	Mistral AI Repo/Distributor: mistralai	Mistral 3.0B	Offizielle Variante provider differs from inferred base provider	82 hoch	open_weight published	Quelle
Ministral 3 3B Instruct 2512 BF16 Basismodell: Mistral 3B	Mistral AI Repo/Distributor: mistralai	Mistral 3.0B	Offizielle Variante provider differs from inferred base provider	82 hoch	open_weight published	Quelle
Ministral 3 8B Instruct 2512 BF16 Basismodell: Mistral 8B	Mistral AI Repo/Distributor: mistralai	Mistral 8.0B	Offizielle Variante provider differs from inferred base provider	82 hoch	open_weight published	Quelle
ERNIE 4.5 0.3B PT Basismodell: ERNIE 0.3B	Baidu Repo/Distributor: baidu	ERNIE 0.3B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE Image Basismodell: ERNIE 8B	Baidu Repo/Distributor: baidu	ERNIE 8.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 0.3B Base PT Basismodell: ERNIE 0.3B	Baidu Repo/Distributor: baidu	ERNIE 0.3B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 21B A3B PT Basismodell: ERNIE 21B	Baidu Repo/Distributor: baidu	ERNIE 21.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 21B A3B Thinking Basismodell: ERNIE 21B	Baidu Repo/Distributor: baidu	ERNIE 21.0B	Offizielle Variante	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 300B A47B PT Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 VL 28B A3B PT Basismodell: ERNIE 28B	Baidu Repo/Distributor: baidu	ERNIE 28.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 VL 28B A3B Thinking Basismodell: ERNIE 28B	Baidu Repo/Distributor: baidu	ERNIE 28.0B	Offizielle Variante	82 hoch	open_weight pending_review	Quelle
ERNIE 4.5 VL 424B A47B PT Basismodell: ERNIE 424B	Baidu Repo/Distributor: baidu	ERNIE 424.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
Kimi K2 Base Basismodell: Kimi	Moonshot AI Repo/Distributor: moonshotai	Kimi —B	Basismodell	82 hoch	open_weight pending_review	Quelle
Kimi Linear 48B A3B Base Basismodell: Kimi 48B	Moonshot AI Repo/Distributor: moonshotai	Kimi 48.0B	Basismodell	82 hoch	open_weight pending_review	Quelle
Kimi Linear 48B A3B Instruct Basismodell: Kimi 48B	Moonshot AI Repo/Distributor: moonshotai	Kimi 48.0B	Offizielle Variante	82 hoch	open_weight pending_review	Quelle
Kimi VL A3B Thinking Basismodell: Kimi 3B	Moonshot AI Repo/Distributor: moonshotai	Kimi 3.0B	Offizielle Variante	82 hoch	open_weight pending_review	Quelle
Kimi VL A3B Thinking 2506 Basismodell: Kimi 3B	Moonshot AI Repo/Distributor: moonshotai	Kimi 3.0B	Offizielle Variante	82 hoch	open_weight pending_review	Quelle
K EXAONE 2.0 750B A37B Basismodell: EXAONE 750B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 750.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE 4.0.1 32B Basismodell: EXAONE 32B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 32.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE Deep 2.4B Basismodell: EXAONE 2.4B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 2.4B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE Deep 32B Basismodell: EXAONE 32B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 32.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE Deep 7.8B Basismodell: EXAONE 7.8B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 7.8B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE 3.5 2.4B Instruct Basismodell: EXAONE 2.4B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 2.4B	Offizielle Variante provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE 3.5 32B Instruct Basismodell: EXAONE 32B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 32.0B	Offizielle Variante provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE 4.0 1.2B Basismodell: EXAONE 1.2B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 1.2B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE 4.0 32B Basismodell: EXAONE 32B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 32.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
EXAONE 4.5 33B Basismodell: EXAONE 33B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 33.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
K EXAONE 236B A23B Basismodell: EXAONE 236B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 236.0B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax M1 40k Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax M1 80k Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax Text 01 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax M2.1 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax VL 01 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
MiniMax Text 01 Hf Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
Kimi K2.6 DFlash Basismodell: Kimi	Moonshot AI Repo/Distributor: nvidia	Kimi —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
DeepSeek V4 Flash Base Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
DeepSeek V4 Pro Base Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
DeepSeek V4 Pro DSpark Basismodell: DeepSeek	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM 4.7 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM 5.3 BF16 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM 5.3 Flash BF16 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM Image Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
GLM TTS Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Basismodell provider differs from inferred base provider	78 hoch	open_weight pending_review	Quelle
ERNIE 4.5 21B A3B Paddle Basismodell: ERNIE 21B	Baidu Repo/Distributor: baidu	ERNIE 21.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 300B A47B 2Bits TP4 Paddle Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 300B A47B Paddle Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE Image Aes Basismodell: ERNIE	Baidu Repo/Distributor: baidu	ERNIE —B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 21B A3B Base PT Basismodell: ERNIE 21B	Baidu Repo/Distributor: baidu	ERNIE 21.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 300B A47B 2Bits Paddle Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 300B A47B 2Bits TP2 Paddle Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 300B A47B Base PT Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 300B A47B Base Paddle Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 300B A47B W4A8C8 TP4 Paddle Basismodell: ERNIE 300B	Baidu Repo/Distributor: baidu	ERNIE 300.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 VL 28B A3B Base PT Basismodell: ERNIE 28B	Baidu Repo/Distributor: baidu	ERNIE 28.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 VL 424B A47B Base PT Basismodell: ERNIE 424B	Baidu Repo/Distributor: baidu	ERNIE 424.0B	Basismodell	77 hoch	open_weight candidate	Quelle
ERNIE 4.5 VL 424B A47B Paddle Basismodell: ERNIE 424B	Baidu Repo/Distributor: baidu	ERNIE 424.0B	Basismodell	77 hoch	open_weight candidate	Quelle
K EXAONE 2.0 750B A37B DSpark Basismodell: EXAONE 750B	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE 750.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
EXAONE Path 2.0 Rev EGFR Basismodell: EXAONE	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
EXAONE Path 2.5 Basismodell: EXAONE	LG AI Research Repo/Distributor: LGAI-EXAONE	EXAONE —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
MiniMax M1 40k Hf Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
MiniMax M1 80k Hf Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
SynLogic 32B Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: MiniMaxAI	Qwen 32.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
SynLogic 7B Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: MiniMaxAI	Qwen 7.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
SynLogic Mix 3 32B Basismodell: MiniMax 32B	MiniMax Repo/Distributor: MiniMaxAI	MiniMax 32.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
VTP Base F16d64 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
VTP Large F16d64 Basismodell: MiniMax 64B	MiniMax Repo/Distributor: MiniMaxAI	MiniMax 64.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
VTP Small F16d64 Basismodell: MiniMax	MiniMax Repo/Distributor: MiniMaxAI	MiniMax —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
MiniMax M2.7 DFlash Basismodell: MiniMax	MiniMax Repo/Distributor: nvidia	MiniMax —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Kimi K2.5 Thinking Eagle3 Basismodell: Kimi	Moonshot AI Repo/Distributor: nvidia	Kimi —B	Offizielle Variante provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Kimi K2.6 Eagle3 Basismodell: Kimi	Moonshot AI Repo/Distributor: nvidia	Kimi —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Kimi K2.7 Code DFlash Basismodell: Kimi	Moonshot AI Repo/Distributor: nvidia	Kimi —B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Cli Gym Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Endless Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Openthoughts Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Swesmith Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Termigen Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen35 9B Terminaltraj Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: allenai	Qwen 9.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Dflash Gemma4 12B Block7 Basismodell: DeepSeek 12B	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek 12.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Dspark Gemma4 12B Block7 Basismodell: DeepSeek 12B	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek 12.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Eagle3 Gemma4 12B Ttt7 Basismodell: DeepSeek 12B	DeepSeek Repo/Distributor: deepseek-ai	DeepSeek 12.0B	Basismodell provider differs from inferred base provider	73 mittel	open_weight candidate	Quelle
Qwen3 8B DE Swap Q4 K M GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: 2448FT	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 30B A3B GGUF Basismodell: Qwen 30B	Alibaba / Qwen Repo/Distributor: 6block	Qwen 30.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 32B GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: 6block	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 2.4T A95B GGUF Basismodell: Qwen 95B	Alibaba / Qwen Repo/Distributor: 6block	Qwen 95.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Base GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: 7ven7o	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B Instruct Abliterated Roleplay Tuned GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: AbliteratedAI	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Lumynax Reasoning DeepSeek Prover V2 671B Gguf Basismodell: DeepSeek 671B	DeepSeek Repo/Distributor: AbteeXAILab	DeepSeek 671.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 32B Instruct AdiTurbo GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: Adiuk	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 72B Instruct AdiTurbo GGUF Basismodell: Qwen 72B	Alibaba / Qwen Repo/Distributor: Adiuk	Qwen 72.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Adi Qwen2.5 14B GLM 5.2 General GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: AdvancedDataIntelligence	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Adi Qwen2.5 7B Ablit GLM 5.2 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: AdvancedDataIntelligence	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Adi Qwen2.5 Coder 7B Kimi 2.7 Code GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: AdvancedDataIntelligence	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Adi Qwen3 8B GLM 5.2 General GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: AdvancedDataIntelligence	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Adi Qwen3.5 4B GLM 5.2 General GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: AdvancedDataIntelligence	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Adi Qwen3.5 9B GLM 5.2 General GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: AdvancedDataIntelligence	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B Instruct GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: AiAF	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Fuse 2 Qwen3.5 4B GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Akahsizrr	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B DFlash2 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Akicou	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 14B DSpark GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: Anbeeld	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct Bposit8 Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: Anomly	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct OBLITERATED Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: ArRENCEAI	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Obliterated Improved Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: ArRENCEAI	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen25 1.5B Gguf Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: ArthurPark	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: AstraiaAI	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 30B A3B Vietnamese Instruct GGUF Basismodell: Qwen 30B	Alibaba / Qwen Repo/Distributor: BachDaThan	Qwen 30.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash Vision Exp Q8 0 MXFP4 Q3 K Q2 K Mixed GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: BahamutRU	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Reranker 4B Q3 K S GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Bearserker	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B ABLITERATED GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Blackfrost-AI	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Q4 K M Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: Bluerosesbutterfly	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Coder 42B A3B Instruct TOTAL RECALL MASTER Coder M 512k Ctx W4A16 Q8 0 GGUF Basismodell: Qwen 42B	Alibaba / Qwen Repo/Distributor: BoneMangler	Qwen 42.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Haskell Rust Python IQ4 XS GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: BoneMangler	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Haskell Rust Python Q6 K GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: BoneMangler	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Typhoon2 Qwen2.5 7B Instruct GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: CaldarianX	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B Q4 K M.gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Chrizly	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Unsloth Qwen3.6 27B NVFP4 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: CodeFault	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5.gguf Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: CrocoCpp	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct FP8 Dynamic TR171 Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Crusadersk	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct FP8 Dynamic TR171 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: Crusadersk	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct Q4 K M GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: DEV-iL	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Dolphin3.0 Qwen2.5 1.5B GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Dennisthemennis69	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Sarathi Qwen2.5 0.5B Instruct GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: DevDPParikh	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen.Qwen3 VL 235B A22B Instruct GGUF Basismodell: Qwen 235B	Alibaba / Qwen Repo/Distributor: DevQuasar	Qwen 235.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: DevinMox	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Dhptl	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 32B Instruct GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: Dhptl	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Dhptl	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 128GB RAM IK GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: Downtown-Case	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: DumbGranny67	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct CodeInfused IQ3 XXS GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct GTAP V3 IQ3 XXS GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct GTAP V3 Q4 K M GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct CodeInfused IQ3 XXS GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct GTAP V3 IQ3 XXS GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct GTAP V3 Q4 K M GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct GTAP Q4 K M GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct CodeInfused IQ3 XXS GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct GTAP V3 IQ3 XXS GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct GTAP V3 Q4 K M GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Math 7B Instruct CodeInfused IQ3 XXS GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Math 7B Instruct GTAP V3 IQ3 XXS GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Math 7B Instruct GTAP V3 Q4 K M GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B TAP DPQ V6 GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: DuoNeural	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 32B Qwople GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: Ebumping	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Agents A1 80 20 Beta GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: Elsephire	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Holo 3.1 35B A3B 80 20 Beta GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: Elsephire	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Ornith 80 20 Beta GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: Elsephire	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Vocabulary Trimming GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: Elsephire	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B Mtp Gguf Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: EnclaveHost	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 0.8B Heretic GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 0.8B Heretic Imatrix GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 2B Heretic GGUF Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 2B Heretic Imatrix GGUF Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B Heretic GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B Heretic Imatrix GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Heretic GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Heretic Imatrix GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
QwenPaw Flash 9B Heretic GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
QwenPaw Flash 9B Heretic Imatrix GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: FadedRedStar	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Frosty40	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next FP8 Abliterixed GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: GlobalCybersecurityAlliance	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen Flash Abliterated Strata GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Hanselor	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen Image 2.1 UltraFast GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Haverbex	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct INT8 Quanto Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: Helllbos	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Fp8 Gulf Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: HeshamSA	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Mxfp4 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: HeshamSA	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Mxfp4 Gulf Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: HeshamSA	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Mxfp4 Mixed Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: HeshamSA	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Mxfp4 Msa Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: HeshamSA	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 30B A3B Instruct 2507 MXFP8 FP8KV CT AutoRound Basismodell: Qwen 30B	Alibaba / Qwen Repo/Distributor: INCModel	Qwen 30.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui Qwen3.8 27B Abliterated VAL APEX I MiniPlus V2.1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: IsValorum	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui Qwen3.8 27B Abliterated VAL APEX I NanoPlus GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: IsValorum	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B EfficientThink Uncensored VAL APEX I MiniPlus V2.1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: IsValorum	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B EfficientThink Uncensored VAL APEX I NanoPlus GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: IsValorum	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B VAL APEX I MiniPlus V3 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: IsValorum	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B VAL APEX I NanoPlus V3 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: IsValorum	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B Prime GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Jadson	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Dirk Qwen3.8 9B GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: JamieBradfield	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Q5 K M GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: Jerem62	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 32B Instruct Heretic GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: Johnblick187	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: KissMyShinyArse	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder Instruct GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Kj0rdan	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Nf4 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: Knightly9	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui Qwen3.8 27B Abliterated GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: LeeMantras	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Lean Eval GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Lemmy00	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Humanlike Chat GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: LessThanThreeAI	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Voxsum Qwen35 0.8B GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: Luigi	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Smartgovt qwen Gguf Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Mallikarjunareddy45	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B A3B Coder MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: ManniX-ITA	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct SmartCockpit V1 F16 Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Marcus0304	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct SmartCockpit V1 Q4 k m Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Marcus0304	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B IQ1 M GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: MarxistLeninist	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Gokdogan Thermal Json Vision New Qwen3.5 4B Vision Gguf Q5 k m Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Merttemur06	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Abliterated GSQ RCO IQ3 XXS Calibrated GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Methane	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: Mha-F	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 1.7B Base GGUF Basismodell: Qwen 1.7B	Alibaba / Qwen Repo/Distributor: MichaelAndrewFischer	Qwen 1.7B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2 5 Unsloth FT Ggufmodel Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: MobiusGaian	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B Nahida RP V2 GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Moranyunchen	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Mungert	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Mungert	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 35B A3B APEX GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: Myric	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B NVFP4 Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: nvidia	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen Image 2.1 Uncensored GGUF Backup Best Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Nexylll	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B MTP GGUF SPLIT Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Nielk38	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 0.5B Instruct GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: NoxNotreve	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 14B Instruct GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: NoxNotreve	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 3B Instruct GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: NoxNotreve	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: NoxNotreve	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 0.6B Q8 Gguf Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: O6lvl4	Qwen 0.6B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 1.7B Q8 Gguf Basismodell: Qwen 1.7B	Alibaba / Qwen Repo/Distributor: O6lvl4	Qwen 1.7B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B OBLITERATED Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: OBLITERATUS	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
OpenYourMind Qwen3.6 35B A3B Abliterated Uncensored APEX GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: OpenYourMind	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
OpenYourMind Qwen3.6 35B A3B Kuato DPO Abliterated Uncensored GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: OpenYourMind	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next PaoAI STRIX BALANCED 2 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: PaoAI	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B LowDrift UD IQ4 XS MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: QQZ2026	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
RK1828 LLM Qwen2.5 7B Instruct Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: RKNNAI	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
RK1828 VLM Qwen2.5 VL 7B Instruct Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: RKNNAI	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
RK182X LLM Qwen2.5 0.5B Instruct Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: RKNNAI	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
RK182X LLM Qwen2.5 1.5B Instruct Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: RKNNAI	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
RK182X LLM Qwen2.5 3B Instruct Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: RKNNAI	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
RK182X VLM Qwen2.5 VL 3B Instruct Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: RKNNAI	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 3B Instruct Profesor Albus Dumbledore Gguf Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: RRNicole1014	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B 5090 Goldilocks GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Rabbit-Hole-Ai	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Atlas Finanzas DeepSeek R1 8B GGUF Basismodell: DeepSeek 8B	DeepSeek Repo/Distributor: Rafaelcedav	DeepSeek 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Airport Gguf Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Rakesh44	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 14B Uncensored GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: Riyan200324200324	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 122B A10B Abliterated GGUF Basismodell: Qwen 122B	Alibaba / Qwen Repo/Distributor: RobinsonLabs	Qwen 122.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Abliterated GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: RobinsonLabs	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 122B A10B Uncensored APEX Compact GGUF Basismodell: Qwen 122B	Alibaba / Qwen Repo/Distributor: SC117	Qwen 122.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored FIT GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: SC117	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next GSQ RCO Abliterated GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: SC117	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2512 T2I Vnfp4 Qwen2.5lv 7B Instruct Bf16 Comfyui Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: Saravutw	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4.1 Flash RANMA EXL3 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: SaturnHeaven	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4.1 Flash RANMA Engram GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: SaturnHeaven	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Rhymeai Qwen3.5 4B Gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Shayde182	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Unsloth Qwen3 4B Unsloth Bnb 4bit Q4KM GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Shiv12A	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Terse Coder GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Shockem	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B NVFP4 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Siri0s	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Q2 K GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Sjwjne	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Q4 K M GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Sjwjne	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash Vision Exp UltraOptimised GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: Solstice-AI	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash Vision UNCENSORED GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: Solstice-AI	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen Image 2.1 Uncensored GGUF Ultraoptimised Curated Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Solstice-AI	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Suri Qwen3.8 27B Companion GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: SpaceTimee	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Suri Qwen3.8 27B Uncensored GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: SpaceTimee	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Suri Qwen3.8 27B Uncensored Q3 K L GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: SpaceTimee	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Suri Qwen3.8 27B Uncensored Q3 K M GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: SpaceTimee	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Suri Qwen3.8 27B Uncensored Q4 0 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: SpaceTimee	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Instruct 2507 Abliterated FP8 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Subalzt	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 8B Heretic GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: T-88mph	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B MTP GGUF Tater NoThink Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: TaterTotterson	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: Testaproxx99	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 3B Coding Assistant Gguf Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: Textmate	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 72B Instruct Abliterated GGUF Basismodell: Qwen 72B	Alibaba / Qwen Repo/Distributor: Thaurock	Qwen 72.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Coder 30B A3B Instruct Abliterated GGUF Basismodell: Qwen 30B	Alibaba / Qwen Repo/Distributor: Thaurock	Qwen 30.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Laura En Qwen3 4B GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Theboukadida	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2p5 1p5b Standard Gguf Basismodell: Qwen 5B	Alibaba / Qwen Repo/Distributor: Tife23	Qwen 5.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next WinVulkan GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: TonyMFJ	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
qwen Finetune GGUF Test Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: TraiNC	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 1.5B Instruct Non Censure Uncensored Coder For Android GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Tree-AI-lab	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Tvheadbot1991	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Tvheadbot1991	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: Tvheadbot1991	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 0.6B GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: Vocabook	Qwen 0.6B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Vocabook	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 REAM144 163B DS4 GGUF Basismodell: DeepSeek 163B	DeepSeek Repo/Distributor: WaveCut	DeepSeek 163.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 REAM96 111B DS4 GGUF Basismodell: DeepSeek 111B	DeepSeek Repo/Distributor: WaveCut	DeepSeek 111.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Serow Qwen2.5 0.5B Instruct Gguf Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: WebAIPocket	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 1.5B Instruct Q4 K M GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Wiktor-757hgbvj	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Winery Qwen2.5 1.5B RP Soup GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: WineryLabs	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Winery Qwen3.8 Flash Next Cuvee GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: WineryLabs	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 Ombro V3c GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: Wladastic	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Nova Qwen2.5 3B Gguf Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: YgramJake	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B Q4 K M GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Zionner	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Ektome Qwen2.5 Coder 14B Instruct PristinelyUncensored Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: Zynerji	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Ektome Qwen2.5 Coder 7B Instruct PristinelyUncensored Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: Zynerji	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Ektome Qwen3.5 9B PristinelyUncensored Frac085 GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: Zynerji	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Ektome Qwen3.6 27B PristinelyUncensored GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: Zynerji	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Swift 1.5 Qwen3.8 27B Uncensored Dynamic MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: ajgazin	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 1.5B Q8 0 GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: alal123	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Abliterated GSQ RCO IQ2 XS Strata GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: alesha-pro	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Abliterated GSQ RCO IQ3 S Strata GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: alesha-pro	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 14B Instruct Quantized.autoround W4a16 Llmcompressor Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: alishafique	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 14B Instruct Quantized.awq W4a16 Llmcompressor Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: alishafique	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 32B Instruct Quantized.awq W4a16 Llmcompressor Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: alishafique	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 3B Instruct Q4 K M GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: americansquid	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash DS4 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: andreaborio	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B DS4 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: andreaborio	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui Qwen3.6 27B Abliterated GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: andyjack	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui Qwen3.8 27B Abliterated GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: andyjack	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Gguf Basismodell: DeepSeek	DeepSeek Repo/Distributor: antirez	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: apriliacloset	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: aquaduck	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Ai Therapist Qwen3 4B Gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: arnabwithab	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct.gguf Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct AWQ 4bit Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct GGUF 4bit Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct GGUF 8bit Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct Q8 0.gguf Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct AWQ 4bit Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct GGUF 4bit Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct GGUF 8bit Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Q8 0.gguf Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B KR GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: artichoke42	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B KR MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: artichoke42	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 1.7B Teleco Slm GGUF Basismodell: Qwen 1.7B	Alibaba / Qwen Repo/Distributor: arturofierrop	Qwen 1.7B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 8B Houdini VEX V11 GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: ashok969	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: asubah	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: asubah	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash Vision Exp Abliterated GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: audreyt	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
OrcaRouter Qwen3.8 Flash Next Uncensored ModelOpt NVFP4 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: auto7x	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen35 9B Ru Personality V3 Gguf Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: aximi	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B NVFP4 W4A16 MLP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: axiomofmind	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
StrxiAI Qwen2.5 0.5B Q8 0 GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: baranqr	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: batiai	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: batiai	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 VL Reranker 2B GGUF Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: bealore	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: bernquant	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B Heretic Uncensored FINETUNE NEO CODE Di IMatrix MAX GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: bernquant	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: bitlamas	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
ATX Swift 1.5 Qwen3.8 27B Uncensored MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: bjivanovich	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Ling 3.0 Flash GGUF Basismodell: Ling 3.0 Flash	bloomer010 Repo/Distributor: bloomer010	— —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 1.5B Instruct Q4 K M GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: blrrypxl	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Caeleste Speech Qwen2.5 0.5B Instruct Nf4 Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: bschooled	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Lfed Qwen2.5 Coder 14B Sql Gguf Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: build-small-hackathon	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Uncensored Genesis Hermes V3 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: burningfeet	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored Q4 K M GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: bux1ansh4n	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B MTP Pi Reasoning GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: bytkim	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Plus GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: callmechaubey	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Swg Resources Qwen3 VL 8B Compact Gguf Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: carbonitex	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B instruct.Q4 K M.gguf Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: cffcuba	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 14B Internal Med Gguf Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: chenhaodev	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: chiakelvin	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B Instruct Gguf Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: chibifire	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Omni Gguf Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: chibifire	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 0.6B Spesialis Gguf Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: chmdznr	Qwen 0.6B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Samantha Uncensored GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: cloudbjorn	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B Samantha Uncensored GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: cloudbjorn	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: cmp-nct	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Lemon Qwen3.5 2B Gguf Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: craftyapple	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Embed 8B GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: cstr	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 VL 2B Crispembed Gguf Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: cstr	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: cvgro	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
QwenPaw Flash 9B Heretic MTP GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: cvgro	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B SC2 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: cyberenchanter	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen Image 2.1 PE I2I Heretic GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: darrellbest	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen Image 2.1 PE T2I Heretic GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: darrellbest	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: ddh0	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: ddh0	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
RavenX Conjecture Qwen3 8B GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: deadbydawn101	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Cybersecurity Heretic 16bit Q4 K M GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: dhomksa	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B DeepThinking 2507 Q4 K M GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: dilipnswamy	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct Mobile Int4 Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: dispatchAI	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct Server Mobile Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: dispatchAI	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Mobile Int4 Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: dispatchAI	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Q5 Mobile Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: dispatchAI	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Q8 Mobile Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: dispatchAI	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Iol Qwen2.5 14B Instruct AWQ Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: divaspoudel	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
ProactiveInquirer Qwen3 8B GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: dolev31	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Whittle Qwen3.8 35B A3B ONYX GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: el4	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Endy Qwen3.6 CyberSec 35B A3B GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: endystrike	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Anascan Title Qwen3 0.6B GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: erponce	Qwen 0.6B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Code Reasoning V2 Gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: ertghiu256	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 20B Minitron Q4 K M GGUF Basismodell: Qwen 20B	Alibaba / Qwen Repo/Distributor: fadyosman	Qwen 20.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui Qwen3.5 9B Abliterated Grimoire DPO GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: fairy322	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored GP100 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: fallentree	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
B14 Qwen25 05B Independent Comparator V1 Recovery GGUF Basismodell: Qwen 5B	Alibaba / Qwen Repo/Distributor: farguney	Qwen 5.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct Gguf Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: forkjoin-ai	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: forkjoin-ai	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 8B Gguf Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: forkjoin-ai	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B NVFP4 Gguf Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: g0chu	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 VL 8B Instruct Abliterated IQ3 XXS GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: geantendormi	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash Gguf Basismodell: DeepSeek	DeepSeek Repo/Distributor: ginokent	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Reranker 0.6B GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: gorse-io	Qwen 0.6B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Q2 0 H64 S4 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: groxaxo	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
ThinkingCap Qwen3.8 27B Abliterated UD Q4 K XL GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: groxaxo	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 DIQ3S GIQ1S UIQ1M GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: hampsonw	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Meeting Summary Gguf Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: hananeek2	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: hardcoremoore	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: hardknocks	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Apostate Gguf Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: heterodoxin	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Abliterated MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: hotdogs	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B ROCmFPX GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: hugobugo34	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui Qwen3 VL 8B Instruct Abliterated FP8 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: huihui-ai	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 235B A22B Instruct 2507 MXFP8 CT AutoRound Basismodell: Qwen 235B	Alibaba / Qwen Repo/Distributor: intel-ai	Qwen 235.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen Qwen3 14B GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: isotonic1	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 1.5B Instruct Abliterated GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: issoufzousko07	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored OptiQ 4bit Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: j-llm	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B AEON RYS Agentic Coder PatchCode GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: jackasda211233	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
ATX Swift 1.5 Qwen3.8 27B Uncensored IQ4 XS M GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: jakeatx	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Instruct 2507 GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: jc-builds	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 0.8B Q4 K M GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: jc-builds	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 2B Q4 K M GGUF Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: jc-builds	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Coder Next Eagle3 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: jdluzen	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Swift 1.5 Qwen3.8 27B Heretic GSQ RCO GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: jegreene	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: jimbothigpen	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B Instruct DASHQ Q2 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: jkim96	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 Antirez Ds4 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: jmilnz	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B SOMPOA Heresy V2 MTP Q4 K M GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: johndoe00000	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 14B Instruct Bnb 4bit Bpmn React Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: jojojo154152we	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct Bpmntoreactjs Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: jojojo154152we	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Usafi AWQ V1 6 Reasoning Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: jumaodhiss	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B 2507 Persona Legacy GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: juststhjust	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Dendriva Qwen2.5 Coder 3B Instruct Gguf Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: kangsyahrul	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Finnish Titan Uncensored GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: kataguru	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct KanColle Hibiki Verniy GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: keichankotaro	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B VN Master Polymath FINAL GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: khoin68	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
qwen Coder 0.5B Monkesearch Gguf Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: kishl	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 2B Base.gguf Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: kratark	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B AEON Ultimate Uncensored UD GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: lambsea	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: ldov	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 3B Instruct GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: ldov	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 Abliterated Q2K GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: lghupan	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Q6dense GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: ligamentexceed	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct FP8 Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: liodon-ai	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct FP8 Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: liodon-ai	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 3B Instruct FP8 Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: liodon-ai	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct FP8 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: liodon-ai	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct FP8 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: liodon-ai	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Math 1.5B Instruct Imatrix GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: liodon-ai	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 1.7B Base Imatrix GGUF Basismodell: Qwen 1.7B	Alibaba / Qwen Repo/Distributor: liodon-ai	Qwen 1.7B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Cskh Gguf NA3 Cl6 V23 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: longdev37	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Dvkt Gguf NA3 Cl Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: longdev37	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: lstari	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B MTP ONLY GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: lym00	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Instruct 2507 Heretic OpenVINO NF4 NPU Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: machine-made-Fibre	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B Agentic Coder Q6 K GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mahiatlinux	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 235B A22B Instruct 2507 Tq3 G32 Basismodell: Qwen 235B	Alibaba / Qwen Repo/Distributor: manjunathshiva	Qwen 235.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: maxidistination	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Padthai Gguf Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mcham	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Q4 K M GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mhm23efx	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Grays Anatomy 2nd Grade Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: michael10098	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 0.8B NVFP4 MTP GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: michaelw9999	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Codemate Qwen1.5B 8k GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: micymike	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Activity Composition Model 400 Qwen3.5 0.8B Gguf Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: mjpsm	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: mnsims1024	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B Instruct GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mnsims1024	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
qwen Unity Multitask Gguf Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: model-and-data	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct Optiq 3bpw Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: mstyslavity	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B NVFP4 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mudler	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B NVFP4 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mudler	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 14B Instruct Uncensored Q4 K M GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: natemiller1928	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Translate GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: nguyenAI2005	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 8B Finetuned GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: nguyentd	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Brainwaves GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: nightmedia	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 3B Instruct Q6 K GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: niuchao79	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 3B Instruct Q8 0 GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: niuchao79	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Crm Qwen35 4B Cleaner V1 GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: noalibi99	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 0.8B GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: notschmee	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Writing DPO GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: nuofang	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B DFlash GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: onion515	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Next 40B Exp MoE Healed GGUF Basismodell: Qwen 40B	Alibaba / Qwen Repo/Distributor: osk-arr00	Qwen 40.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 9B Pi 2 Q4 0 GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: owenqwenllmwine	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: ox-ox	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Q4 k M.gguf Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: papineau1837	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct 1M Gguf F16 Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: pbhappliedsystems	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct 1M Gguf Q4 K M Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: pbhappliedsystems	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 32B Instruct Gguf F16 Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: pbhappliedsystems	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 32B Instruct Gguf Q4 K M Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: pbhappliedsystems	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Gguf F16 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: pbhappliedsystems	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Dagger Qwen3.6 27B GGUF MTP Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: peculiar-ragdoll	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Q3 Mlx Cba Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: plawanrath	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Q4 Mlx Cba Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: plawanrath	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Q6 Mlx Cba Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: plawanrath	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Q8 Mlx Cba Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: plawanrath	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B DS V4 Flash V1.0 GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: prithivMLmods	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: prometheusAIR	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 VL 32B Instruct NVFP4 Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: protofu	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: purdue-ie336	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 3B Instruct GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: purdue-ie336	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored Q4 K M GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: qaqab	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 VL 8B Instruct Abliterated V2 GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: qign	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 0.8B Base Mmproj GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: qikp	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B Instruct GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: qingjiaofanqi	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui Qwen3 VL 8B Instruct Abliterated AWQ Int4 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: quant-mind	Qwen 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Hindi Imatrix Q4 K M GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: rajasaini2208	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 2B LQ8 GGUF Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: reecdev	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Scrubdata Qwen3 4B Gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: ricalanis	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Scrubdata Qwen3 4B V4 Gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: ricalanis	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen Image 2.1 Uncensored Abenzerps GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: robertbschuette	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Huihui qwen3 5 9B Mxfp4 Gguf Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 14B Heretic Mxfp4 Gguf Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen36 27B Heretic Mxfp4 Gguf Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen36 35B A3B Mxfp4 Gguf Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Safe Huihui qwen3 5 9B Mxfp4 Gguf Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Safe qwen3 14B Heretic Mxfp4 Gguf Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Safe qwen36 27B Heretic Mxfp4 Gguf Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Safe qwen36 35B A3B Mxfp4 Gguf Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Sese Huihui qwen35 9B Mxfp4 Gguf Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 9.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Sese qwen3 14B Heretic Mxfp4 Gguf Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Sese qwen36 27B Heretic Mxfp4 Gguf Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Sese qwen36 35B A3B Heretic Mxfp4 Gguf Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: robinshao	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Pro 0813 Gguf Basismodell: DeepSeek	DeepSeek Repo/Distributor: ryant0000	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct Heretic Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Heretic Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct Heretic Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 3B Instruct Heretic Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct 1M Heretic Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Heretic Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 0.5B Instruct Heretic Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 3B Instruct Heretic Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct Heretic Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B Instruct Heretic Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: saidutta69	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 Antirez Ds4 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: schlaflos	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Globe Theatre Qwen25 3B Gguf Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: sdavies	Qwen 3.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 35B A3B BitClass3 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: sh111111111111111	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 0.6B Agentic Terminal GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: shr3y	Qwen 0.6B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 6 KMP Dev GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: siendsi	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Vanellypet Qwen3 4B Gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: sjinji	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Q6 k Gguf Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: sli3	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Delivery Qwen2.5 7B Driver Gguf Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: sonysum	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Cyberneurova Qwen3.8 Flash Next GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: spiritfather	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
It Sector qwen Gguf Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: sree123-123	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
It qwen Gguf Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: sree123-123	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Stiles Seymens Qwen2.5 7B Generalist Q4KM GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: sseymens	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 0.8B Q4 K M GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: tamerbaydag	Qwen 0.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 4B Q4 K M GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: tamerbaydag	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4.1 Flash GSQ RCO GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: taurusduan	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Swift Qwen3.8 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: taurusduan	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Strixflash GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: tawei-amd	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Coder 30B A3B Instruct GGUF Basismodell: Qwen 30B	Alibaba / Qwen Repo/Distributor: td-builder	Qwen 30.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 27B ThinkSonic Coder Dare Ties MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: tepirale	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 32B Instruct GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: thecodehaider	Qwen 32.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen36 27B Heretic MTP GGUF Q5 Vision Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: themacaw	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2 Legal GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: thin-hu	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Muta Tutor Qwen2.5 1.5B ADTC GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: timiiowolabi	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.5 2B GGUF JAVA Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: tmih06	Qwen 2.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B ZipBrain GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: tooltd	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 14B A3B VibeForged V2 GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: tvall43	Qwen 14.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct AWQ Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: tzervas	Qwen 1.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B Thinking 4 Gguf Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: uberkie	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct NVFP4A16 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: uist-labs	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Hy MT2 1.8B GGUF Basismodell: Hy MT2 1.8B	unsloth Repo/Distributor: unsloth	Hy-MT2 1.8B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Hy MT2 7B GGUF Basismodell: Hy MT2 7B	unsloth Repo/Distributor: unsloth	Hy-MT2 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
LFM2.5 8B A1B GGUF Basismodell: LFM2.5 8B A1B	unsloth Repo/Distributor: unsloth	LFM2.5 8.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Step 3.7 Flash GGUF Basismodell: Step 3.7 Flash	unsloth Repo/Distributor: unsloth	Step —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
AxiomAi Qwen2.5 Coder 7B Instruct GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: userIncognitoe-1	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored HauhauCS Aggressive MTP GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: vanchi34200	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 27B Architect Polaris2 Fable B F451 MTP ROCmFPX GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: vmlinux	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
ASB Qwen2.5 Coder 7B Targeted V2 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: weahoo	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Sex GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: why4567890	Qwen —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct FP8 Dynamic Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: wrbooth	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Uncensored xCloud GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: xCloudinfo	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash Vision Exp UD Q4 K XL.LAYR.GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: xautonomics	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 0.6B Q4 0 GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: xuhuaze	Qwen 0.6B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
DeepSeek V4 Flash MXFP4 Mixed LLMC 4layers Basismodell: DeepSeek	DeepSeek Repo/Distributor: xwu-intel	DeepSeek —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Yoiko Img Prompt Gen Qwen2.5 7B Instruct Q4 K M Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: yoikoarmor	Qwen 7.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 4B ORPO Advertisement GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: yothinS	Qwen 4.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Uncensored Genesis Hermes GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: yuhanb	Qwen 35.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 Coder 0.5B Trident Deep V4.2 Gguf Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: yuiseki	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen3 Next 80B A3B Thinking APEX GGUF Basismodell: Qwen 80B	Alibaba / Qwen Repo/Distributor: zTrojan	Qwen 80.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
GLM 5 FP8 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
GLM 5.1 FP8 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
GLM 5.2 FP8 Basismodell: GLM	Z.ai / Zhipu AI Repo/Distributor: zai-org	GLM —B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Q5 0 GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: zed122	Qwen 0.5B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Nerkyor Qwen3.8 27B EfficientThink KQVQ4 IQ3Floor 10G MTP Fast GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: zhangrover	Qwen 27.0B	Quantisierung quantization not base model	70 mittel	open_weight verified	Quelle
Dflash qwen3 14B Block7 Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 14.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dflash qwen3 4B Block7 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 4.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dflash qwen3 8B Block7 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 8.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dspark qwen3 14B Block7 Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 14.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dspark qwen3 4B Block7 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 4.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Dspark qwen3 8B Block7 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 8.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Eagle3 qwen3 14B Ttt7 Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 14.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Eagle3 qwen3 4B Ttt7 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 4.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Eagle3 qwen3 8B Ttt7 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: deepseek-ai	Qwen 8.0B	Basismodell deepseek name but family provider mismatchprovider differs from inferred base provider	69 mittel	open_weight candidate	Quelle
Qwen3.8 Flash Next GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Baekpica	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Mixed Quant GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Baekpica	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Uncensored Mixed Quant SSD PLE GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: Baekpica	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: DavidAU	Qwen 9.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
DeepSeek V4 Pro Qwen3.5 9B Q4 K M GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: EsmondH	Qwen 9.0B	Quantisierung deepseek name but family provider mismatchquantization not base model	66 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Uncensored Genesis GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: LuffyTheFox	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Uncensored Genesis Hermes V4 MTP GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: LuffyTheFox	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Uncensored Genesis V3 APEX GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: LuffyTheFox	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 4B GymGPT Pro AR EN Instruct AWQ Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: Mohamed132411	Qwen 4.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 1.5B Instruct Pollard Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: PollardWeights	Qwen 1.5B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Meta Llama 3.1 8B Instruct Quantized.w8a8 Basismodell: Llama 8B	Meta Repo/Distributor: RedHatAI	Llama 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Quantized.w4a16 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: RedHatAI	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 3B Instruct Quantized.w4a16 Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: RedHatAI	Qwen 3.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 72B Instruct Quantized.w4a16 Basismodell: Qwen 72B	Alibaba / Qwen Repo/Distributor: RedHatAI	Qwen 72.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 122B A10B Opus Reasoning MTP GGUF Basismodell: Qwen 122B	Alibaba / Qwen Repo/Distributor: SixVolts	Qwen 122.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 14B Instruct quantized.GPT q W4a16 Llmcompressor Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: alishafique	Qwen 14.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 32B Instruct quantized.GPT q W4a16 Llmcompressor Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: alishafique	Qwen 32.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct GPT Q 4bit Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 0.5B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct GPT Q 4bit Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 14.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 14B Instruct GPT Q 8bit Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 14.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct GPT Q 4bit Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 7.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct GPT Q 8bit Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: arthuravianna	Qwen 7.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
rpDungeon Gemma4 31B Gembrain Equinox GGUF Basismodell: Gemma 31B	Google Repo/Distributor: bartowski	Gemma 31.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
RobloxGPT Qwen2.5 Coder 3B GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: cg2020	Qwen 3.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
DeepSeek R1 671B Q4 K M Basismodell: DeepSeek 671B	DeepSeek Repo/Distributor: deepseek2	DeepSeek 671.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
DeepSeek V3.1 671B Basismodell: DeepSeek 671B	DeepSeek Repo/Distributor: deepseek2	DeepSeek 671.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Qwen2.5 1.5B Instruct GPT q 4bit Mlx Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: dfed24	Qwen 1.5B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 3B Instruct GPT Q A16w4 Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: florianvoss	Qwen 3.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen3 VL 8B Instruct GPT Q A16w4 Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: florianvoss	Qwen 8.0B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Gemma 3 12B Basismodell: Gemma 12.2B	Google Repo/Distributor: gemma3	Gemma 12.2B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Gemma 3 27B Basismodell: Gemma 27.4B	Google Repo/Distributor: gemma3	Gemma 27.4B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Gemma 3 4B Basismodell: Gemma 4.3B	Google Repo/Distributor: gemma3	Gemma 4.3B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Qwen3 0.6B Base GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: ggml-org	Qwen 0.6B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 0.8B Base GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: ggml-org	Qwen 0.8B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 0.8B GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: ggml-org	Qwen 0.8B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
GPT OSS 20B Basismodell: GPT OSS 20.9B	OpenAI Repo/Distributor: gptoss	GPT-OSS 20.9B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	local_runtime verified	Quelle
Qwen3.8 Flash Next Uncensored ROCmFP4 FAST Imatrix GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: kingjones777	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Uncensored ROCmFP4 STRIX LEAN GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: kingjones777	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next Uncensored ROCmFP4 STRIX LEAN Imatrix GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: kingjones777	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Codellama 34B Basismodell: Llama 34B	Meta Repo/Distributor: llama	Llama 34.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Llama 3 70B Basismodell: Llama 70.6B	Meta Repo/Distributor: llama	Llama 70.6B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Llama 3.1 70B Basismodell: Llama 70.6B	Meta Repo/Distributor: llama	Llama 70.6B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Llama 3.1 8B Basismodell: Llama 8B	Meta Repo/Distributor: llama	Llama 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Llama 3.1 Storm 8B Q4 K M Basismodell: Llama 8B	Meta Repo/Distributor: llama	Llama 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Llama 3.2 1B Basismodell: Llama 1.2B	Meta Repo/Distributor: llama	Llama 1.2B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Llama 3.2 3B Basismodell: Llama 3.2B	Meta Repo/Distributor: llama	Llama 3.2B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
A3 Qwen3 14B GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 14.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ATPO G Qwen2.5 VL 7B R0.2 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
AceCoder Qwen2.5 Coder 7B Base Rule GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
AgentMercury Qwen3.5 4B GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
CampoTech Qwen2.5 7B Agricola GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
DeepControl Qwen2.5 7B GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Docto Decision Qwen3.5 4B Fr V0.1 GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
DreamFast Qwen3 4B Heretic GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
DreamFast Qwen3 8B Heretic GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Ektome Qwen2.5 VL 3Bi PristinelyUncensored I1 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Ektome Qwen3 30B A3B PristinelyUncensored GGUF Basismodell: Qwen 30B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 30.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Ektome Qwen3 VL 4Bi PristinelyUncensored I1 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Elster Vernunft Qwen3.6 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
FACET Terminal Qwen3.5 4B GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
FACET Terminal Qwen3.5 9B GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 9.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
H100 Qwen3 14B MonEspaceSante CPT GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 14.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
H100 Qwen3 14B MonEspaceSante CPT I1 GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 14.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Huihui Qwen3.8 27B Coder390 EfficientThink Abliterated GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Huihui Qwen3.8 Flash Next Abliterated GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Iconoclast Qwen2.5 0.5B GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.5B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Kahn1 Qwen2.5 3B GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 3.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
LightThinker Plus Qwen GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
LightThinker Plus Qwen I1 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Loes Qwen3.8 27B I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
MachiNoDolphin Qwen2.5 72B GGUF Basismodell: Qwen 72B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 72.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Medgap Qwen3.8 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Medhal Qwen3 8B GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Ostrich 27B Qwen3.8 260815 I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Pathumma ThaiLLM Qwen3 8B Think 2.0.0 GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct OBLITERATED GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.5B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 0.5B Instruct OBLITERATED I1 GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.5B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Uncensored I1 GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 1.5B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 14B OBLITERATED GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 14.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 14B OBLITERATED I1 GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 14.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 32B Translation GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 32.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 72B Instruct Heretic GGUF Basismodell: Qwen 72B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 72.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 72B Instruct Heretic I1 GGUF Basismodell: Qwen 72B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 72.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct 1M Heretic I1 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct OBLITERATED GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct OBLITERATED I1 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Obliterated Improved GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct Obliterated Improved I1 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 7B OBLITERATED GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 7B OBLITERATED I1 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 0.5B Instruct Heretic GGUF Basismodell: Qwen 0.5B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.5B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 14B Instruct Heretic GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 14.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 32B Python Specialist GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 32.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 32B Python Specialist I1 GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 32.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct OBLITERATED Advanced GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 Coder 7B Instruct OBLITERATED Advanced I1 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 Furry 7B GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 Furry 7B I1 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 R1 Minny 1.5B V2 GGUF Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 1.5B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 32B Instruct Abliterated I1 GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 32.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 32B Instruct Heretic GGUF Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 32.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 3B Gearbox GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 3.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 3B Instruct Heretic GGUF Basismodell: Qwen 3B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 3.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B HyperClick GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2.5 VL 7B Instruct Heretic GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen2vl Model 2B Instruct Spatial Information V1 GGUF Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 2.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 0.6B Abliterated I1 GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.6B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 0.6B BrowserAgent GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.6B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 0.6B BrowserAgent I1 GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.6B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 0.6B Heretic Base I1 GGUF Basismodell: Qwen 0.6B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.6B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 1.7B Abliterated I1 GGUF Basismodell: Qwen 1.7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 1.7B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 1.7B Abliterated V2 GGUF Basismodell: Qwen 1.7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 1.7B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 1.7B Abliterated V2 I1 GGUF Basismodell: Qwen 1.7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 1.7B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 1.7B L6 Abliterated I1 GGUF Basismodell: Qwen 1.7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 1.7B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 14B PragReST I1 GGUF Basismodell: Qwen 14B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 14.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 30B A3B Element7 1M GGUF Basismodell: Qwen 30B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 30.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 4B Alucard GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 4B Thinking Heretic GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 4B Uncensored GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 8B Apostate GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 8B Apostate I1 GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 8B MedReasonPath GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 8B PragReST GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 8B PragReST I1 GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 Coder 64B I1 GGUF Basismodell: Qwen 64B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 64.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 Coder Next REAM I1 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 Coder Next Uncensored Heretic I1 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 VL 4B Instruct Uncensored Abliterated GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 VL 8B Instruct Heretic GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 0.8B Uncensored GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.8B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 27B Derestricted I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 4B Kazakh GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 9B Brainwaves GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 9.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 9B Egyptian 1 GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 9.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 9B Ultra Uncensored Heretic V1 I1 GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 9.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 9B Ultra Uncensored Heretic V2 I1 GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 9.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 KETI HAECHI 27B I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 27B AEON Ultimate Uncensored BF16 I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 27B Esper4 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 27B Esper4 I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Brainwaves Nex Uncensored I1 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B StyleTune GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B StyleTune I1 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B Uncensored HauhauCS FP16 I1 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 35B V2 MoE Ablit Heretic Uncensor Hermes MTP Vision FT I1 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B Fimi 2 I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B Human KO Enterprise Boundary I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B MTP Heretic Ja GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B MindMeld I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B Optimal Ablit Heretic I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B Refusal Ablation L46 A0.25 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored Aggressive GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 27B Uncensored Aggressive I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 Flash Coder 85gb Bf16 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next REAM 60Pct GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.8 Flash Next REAM 60Pct I1 GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen35B A3B SignOfFour Coder GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen35B A3B SignOfFour Coder I1 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen35B Agent R2 Abliterated I1 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
SkillGym Qwen3.5 9B GGUF Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 9.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Socratic Qwen2.5 7B V2 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Sofia Qwen2.5 7B GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Sofia Qwen2.5 7B I1 GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
SteyrCannon Qwen2.5 72B GGUF Basismodell: Qwen 72B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 72.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Suri Qwen3.8 27B Neuro I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Susi Qwen3 4B Thinking 2507 GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Swift 1.5 Qwen3.8 27B Abliterated GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Swift 1.5 Qwen3.8 27B Abliterated I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Swift 1.5 Qwen3.8 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Swift 1.5 Qwen3.8 27B Heretic I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Swift 1.5 Qwen3.8 27B I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Swift 1.5 Qwen3.8 27B Uncensored BF16 I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Swift Qwen3.8 27B Uncensored MTP Terse Coder I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Terminal Lego Qwen3 8B GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ThinCtx Qwen3.5 0.8B GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.8B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ThinCtx Qwen3.5 0.8B I1 GGUF Basismodell: Qwen 0.8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 0.8B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ThinCtx Qwen3.5 2B GGUF Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 2.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ThinCtx Qwen3.5 2B I1 GGUF Basismodell: Qwen 2B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 2.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ThinCtx Qwen3.5 4B GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ThinkingCap Qwen3.6 27B GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ThinkingCap Qwen3.8 27B I1 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
ToolSpace Qwen3 30B A3B GGUF Basismodell: Qwen 30B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 30.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Tvall43 Qwen3.5 4B Heretic V2 GGUF Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 4.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
VideoKR Qwen2.5 VL 7B GGUF Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 7.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
VideoKR Qwen3 VL 8B GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: mradermacher	Qwen 8.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.5 9bxOpus 4.7 Sonic GGUF Basismodell: Qwen	Alibaba / Qwen Repo/Distributor: nphearum	Qwen —B	Quantisierung claimed distill or name reference needs reviewquantization not base model	66 mittel	open_weight verified	Quelle
Qwen3.6 27B OBLITERATED MTP ROCmFP4 GGUF Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: plunderstruck	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 35B A3B MTP ROCmFP4 GGUF Basismodell: Qwen 35B	Alibaba / Qwen Repo/Distributor: plunderstruck	Qwen 35.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 40B Deckard MTP ROCmFP4 GGUF Basismodell: Qwen 40B	Alibaba / Qwen Repo/Distributor: plunderstruck	Qwen 40.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 14B Basismodell: Qwen 14.8B	Alibaba / Qwen Repo/Distributor: qwen3	Qwen 14.8B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Qwen3 32B Basismodell: Qwen 32.8B	Alibaba / Qwen Repo/Distributor: qwen3	Qwen 32.8B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Qwen3 8B Basismodell: Qwen 8.2B	Alibaba / Qwen Repo/Distributor: qwen3	Qwen 8.2B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
Qwen3 Coder 30B Basismodell: Qwen 30.5B	Alibaba / Qwen Repo/Distributor: qwen3moe	Qwen 30.5B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	local_runtime verified	Quelle
DeepSeek R1 0528 Qwen3 8B Heretic GGUF Basismodell: Qwen 8B	Alibaba / Qwen Repo/Distributor: richardyoung	Qwen 8.0B	Quantisierung deepseek name but family provider mismatchquantization not base model	66 mittel	open_weight verified	Quelle
DeepSeek V4 Flash 0731 GGUF Basismodell: DeepSeek	DeepSeek Repo/Distributor: unsloth	DeepSeek —B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3.6 27B NVFP4 Basismodell: Qwen 27B	Alibaba / Qwen Repo/Distributor: unsloth	Qwen 27.0B	Quantisierung quantization not base modelrepository owner not base provider	66 mittel	open_weight verified	Quelle
Qwen3 4B Instruct Squad Ratio 0.30 R4 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: AlinaGonch	Qwen 4.0B	Adapter/LoRA community or derivative	65 mittel	open_weight verified	Quelle
Qwen3 4B Instruct Squad Ratio 0.50 R4 Basismodell: Qwen 4B	Alibaba / Qwen Repo/Distributor: AlinaGonch	Qwen 4.0B	Adapter/LoRA community or derivative	65 mittel	open_weight verified	Quelle
Qwen2.5 1.5B Instruct Text2sql Lora Basismodell: Qwen 1.5B	Alibaba / Qwen Repo/Distributor: Amr-Kh-2004	Qwen 1.5B	Adapter/LoRA community or derivative	65 mittel	open_weight verified	Quelle
Eddie Woo Hoo Qwen2.5 7B Instruct Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: ApolloRaines	Qwen 7.0B	Adapter/LoRA community or derivative	65 mittel	open_weight verified	Quelle
Qwen2.5 Coder 32B Instruct Jbliterated Basismodell: Qwen 32B	Alibaba / Qwen Repo/Distributor: ApolloRaines	Qwen 32.0B	Adapter/LoRA community or derivative	65 mittel	open_weight verified	Quelle
Qwen3.5 9B Cooper Instruct Sft Basismodell: Qwen 9B	Alibaba / Qwen Repo/Distributor: CooperBench	Qwen 9.0B	Adapter/LoRA community or derivative	65 mittel	open_weight verified	Quelle
Qwen2.5 7B Instruct MBTI Lora2 Basismodell: Qwen 7B	Alibaba / Qwen Repo/Distributor: DrinkIcedT	Qwen 7.0B	Adapter/LoRA community or derivative	65 mittel	open_weight verified	Quelle

Generated: 2026-10-16T09:45:09.114810+00:00

Kuratierter KI-Modellkatalog: lokale LLMs, Open Weights und API-only-Modelle

Katalogqualität sichtbar machen

Kuratierte Ansicht: wichtige Modelle zuerst

Modellfamilien gruppieren statt Variantenflut

Entdeckungsindex mit Rollen-Badges