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
QW
Qwen.Qwen3 32B
Qwen · DevQuasar
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
GL
Allura org.GLM4 32B Neon v2
GLM · DevQuasar
Params32.6B
Context32K
Q4_K_M19.7 GB
GGUF
DM
DMindAI.DMind 3 Mini
Dmind · DevQuasar
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
DE
deepseek ai.DeepSeek V4 Flash Vision Exp
DeepSeek · DevQuasar
Params284B
Context1024K
Smallest103.1 GB
GGUF
AU
Delta Vector.Austral 24B Winton
Austral · DevQuasar
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
GR
Ibm Granite.Granite 4.1 30b
Granite · DevQuasar
Params28.9B
Context128K
Q4_K_M17.5 GB
Tool use
GL
Allura org.GLM4 9B Neon v2
GLM · DevQuasar
Params9.4B
Context32K
Q4_K_M6.2 GB
Tool use
FR
microsoft.FrogBoss 32B 2510
Frogboss · DevQuasar
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
DR
Dream v0 Instruct 7B
Dream · DevQuasar
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
MA
Doctor Shotgun.MS3.2 24B Magnum Diamond
Magnum · DevQuasar
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
NE
nvidia.Orchestrator 8B
Nemotron · DevQuasar
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
MI
teknium.OpenHermes 2.5 Mistral 7B
Mistral · DevQuasar
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
PA
Writer.palmyra Mini Thinking B
Palmyra · DevQuasar
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
AR
inclusionAI.AReaL Boba 2 14B
Areal · DevQuasar
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
CO
nvidia.Cosmos Reason1 7B
Cosmos · DevQuasar
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
HE
NousResearch.Hermes 4 14B
Hermes · DevQuasar
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
QW
iapp.Qwen2.5 VL 7B Instruct
Qwen · DevQuasar
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
NE
nvidia.AceReason Nemotron 1.1 7B
Nemotron · DevQuasar
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
KI
moonshotai.Kimi VL A3B Thinking 2506
Kimi · DevQuasar
Params16B
Context128K
Q4_K_M10.5 GB
ReasoningVision
GE
Google.Gemma 4 12B It Qat Q4_0 Unquantized
Gemma · DevQuasar
Params11.9B
Context256K
Smallest4.8 GB
ReasoningTool use
FO
Fdtn ai.Foundation Sec 8B
Foundation · DevQuasar
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MA
Salesforce.E1 Math 1.5B
Math · DevQuasar
Params1.78B
Context128K
Q4_K_M1.1 GB
Tool use
HU
tencent.Hunyuan 4B Instruct
Hunyuan · DevQuasar
Params4.22B
Context256K
Q4_K_M2.6 GB
ReasoningTool use
JA
ai21labs.Jamba v0.1
Jamba · DevQuasar
Params51.6B
Context256K
Q4_K_M31.2 GB
GGUF
MI
MiniCPM4.1 8B
MiniCPM · DevQuasar
Params8.19B
Context64K
Q4_K_M5.0 GB
Reasoning
MI
Miromind ai.MiroThinker v1.0 72B
Mirothinker · DevQuasar
Params72.7B
Context256K
Q4_K_M47.4 GB
Tool use
LU
Menlo.Lucy
Lucy · DevQuasar
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
DE
NousResearch.DeepHermes Financial Fundamentals Prediction Specialist Atropos
Deephermes · DevQuasar
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Qwen.Qwen3 235B A22B Thinking 2507
Qwen · DevQuasar
Params235B
Context256K
Q4_K_M142.2 GB
ReasoningTool use
QW
Qwen2.5 0.5B Instruct
Qwen · DevQuasar
Params494M
Context32K
Q4_K_M0.4 GB
Tool use

Keep browsing