GGUF models by DevQuasar

833 GGUF models quantized by DevQuasar on Hugging Face. Sizes run from 82M to 2780B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
mistralai.Mistral Small 4 119B 2603 BF16
Mistral · DevQuasar
Params119B
Context1024K
Q4_K_M72.2 GB
Tool use
KI
moonshotai.Kimi K2 Instruct BF16
Kimi · DevQuasar
Params1030B
Context128K
Q4_K_M620.6 GB
Tool use
JA
ai21labs.AI21 Jamba Large 1.7
Jamba · DevQuasar
Params399B
Context256K
Q4_K_M240.3 GB
Tool use
LI
inclusionAI.Ling 1T
Ling · DevQuasar
Params1000B
Context32K
Q4_K_M604.2 GB
ReasoningTool use
AP
ServiceNow AI.Apriel 1.6 15b Thinker
Apriel · DevQuasar
Params14.4B
Context256K
Q4_K_M8.8 GB
ReasoningTool useVision
MI
XiaomiMiMo.MiMo V2.6 Pro RL
Mimo · DevQuasar
Params1020B
Context1024K
Smallest373.5 GB
ReasoningTool useVision
DI
Google.Diffusiongemma 26B A4B It
Diffusiongemma · DevQuasar
Params25.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
TR
Google.Translategemma 4b It
Translategemma · DevQuasar
Params3.88B
Context128K
Q4_K_M2.5 GB
GGUF
CO
CohereLabs.command A Plus 05 2026 Bf16
Command · DevQuasar
Params218B
Context4883K
Smallest79.7 GB
Tool use
QW
Qwen.Qwen3 235B A22B
Qwen · DevQuasar
Params235B
Context40K
Q4_K_M142.2 GB
ReasoningTool use
NE
nvidia.Nemotron Terminal 8B
Nemotron · DevQuasar
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen2.5 32B
Qwen · DevQuasar
Params32.8B
Context128K
Q4_K_M19.9 GB
Tool use
KI
moonshotai.Kimi K2.7 Code
Kimi · DevQuasar
Params1030B
Context256K
Q4_K_M620.6 GB
CodingReasoningTool use
MI
MiniMaxAI.MiniMax M2.7
Minimax · DevQuasar
Params229B
Context192K
Q4_K_M138.3 GB
ReasoningTool use
DE
Deepcogito.Cogito v2 Preview Deepseek 671B MoE
DeepSeek · DevQuasar
Params671B
Context160K
Q4_K_M404.5 GB
ReasoningTool use
QW
Qwen.Qwen3 VL 235B A22B Thinking
Qwen · DevQuasar
Params235B
Context256K
Q4_K_M142.2 GB
ReasoningTool useVision
QW
Qwen.Qwen3 235B A22B Instruct 2507
Qwen · DevQuasar
Params235B
Context256K
Q4_K_M142.2 GB
ReasoningTool use
ME
Google.Medgemma 4b It
Medgemma · DevQuasar
Params3.88B
Context128K
Q4_K_M2.5 GB
Vision
MI
cerebras/MiniMax-M2-REAP-139B-A10B
Minimax · DevQuasar
Params139B
Context192K
Q4_K_M84.2 GB
ReasoningTool use
MI
XiaomiMiMo.MiMo V2 Flash
Mimo · DevQuasar
Params309B
Context256K
Q4_K_M186.8 GB
ReasoningTool use
QW
Qwen.Qwen AgentWorld 35B A3B
Qwen · DevQuasar
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
HE
NousResearch.Hermes 4.3 36B
Hermes · DevQuasar
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
GR
Ibm Granite.Granite 4.0 1b
Granite · DevQuasar
Params1.63B
Context128K
Q4_K_M1.0 GB
Tool use
QW
Huihui ai.Qwen3 4B Abliterated
Qwen · DevQuasar
Params4.02B
Context40K
Q4_K_M2.5 GB
GGUF
MI
MiniMaxAI.MiniMax M3
Minimax · DevQuasar
Params426B
Context1024K
Q4_K_M257.1 GB
ReasoningTool use
QW
Qwen.Qwen2.5 VL 72B Instruct
Qwen · DevQuasar
Params705M
Context125K
Q4_K_M47.4 GB
Vision
JA
ai21labs.AI21 Jamba Mini 1.7
Jamba · DevQuasar
Params51.6B
Context256K
Q4_K_M31.2 GB
Tool use
EU
Utter project.EuroLLM 22B Instruct 2512
Eurollm · DevQuasar
Params22.6B
Context32K
Q4_K_M13.7 GB
GGUF
DE
Deepseek ai.DeepSeek R1 0528 Bf16
DeepSeek · DevQuasar
Params671B
Context160K
Q4_K_M404.5 GB
ReasoningTool use
NE
nvidia.Nemotron Content Safety Reasoning 4B
Nemotron · DevQuasar
Params4.55B
Context128K
Q4_K_M2.9 GB
Reasoning

Keep browsing