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.Qwen3.5 397B A17B
Qwen · DevQuasar
Params396B
Context256K
Q4_K_M240.6 GB
ReasoningTool useVision
HU
Huihui ai.Huihui MoE 4.8B A1.7B Abliterated
Huihui · DevQuasar
Params4.89B
Context40K
Q4_K_M3.0 GB
GGUF
BE
reflection.Beam 1.0 501B A23B
Beam · DevQuasar
Params501B
Context1024K
Smallest182.1 GB
ReasoningTool use
KI
moonshotai.Kimi K2 Thinking
Kimi · DevQuasar
Params1030B
Context256K
Q4_K_M620.6 GB
ReasoningTool use
KI
moonshotai.Kimi K2.6
Kimi · DevQuasar
Params1030B
Context256K
Q4_K_M620.6 GB
ReasoningTool use
MI
unsloth.Devstral Small 2505
Mistral · DevQuasar
Params23.6B
Context128K
Q4_K_M14.3 GB
CodingTool use
QW
Qwen.Qwen3.5 35B A3B
Qwen · DevQuasar
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
PH
microsoft.Phi 4 Reasoning Plus
Phi · DevQuasar
Params14.7B
Context32K
Q4_K_M9.1 GB
Reasoning
QW
Qwen.Qwen3 Reranker 0.6B
Qwen · DevQuasar
Params596M
Context40K
Q4_K_M0.4 GB
EmbeddingReasoningTool use
TI
CohereLabs.tiny Aya Water
Tiny · DevQuasar
Params3.35B
Context488K
Q4_K_M2.1 GB
GGUF
MI
K intelligence.Midm 2.0 Base Instruct
Midm · DevQuasar
Params11.5B
Context32K
Q4_K_M7.0 GB
Tool use
QW
Qwen.Qwen2.5 7B Instruct
Qwen · DevQuasar
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
LL
nvidia.Llama 3 1 Nemotron Ultra 253B CPT v1
Llama · DevQuasar
Params253B
Context128K
Q4_K_M150.9 GB
Tool use
MI
mistralai.Ministral 3 8B Reasoning 2512
Mistral · DevQuasar
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningTool useVision
QW
Qwen.Qwen3 Coder 480B A35B Instruct
Qwen · DevQuasar
Params480B
Context256K
Q4_K_M290.1 GB
CodingTool use
MI
cerebras/MiniMax-M2-REAP-162B-A10B
Minimax · DevQuasar
Params162B
Context192K
Q4_K_M98.0 GB
ReasoningTool use
MO
facebook.MobileLLM R1 950M
Mobilellm · DevQuasar
Params950M
Context32K
Q4_K_M0.6 GB
ReasoningTool use
NE
nvidia.NVIDIA Nemotron Nano 9B v2 Japanese
Nemotron · DevQuasar
Params8.89B
Context1024K
Q4_K_M6.5 GB
ReasoningTool use
IQ
IQuestLab.IQuest Coder V1 14B Instruct
Iquest · DevQuasar
Params14.4B
Context128K
Q4_K_M8.8 GB
CodingTool use
MI
MiniMaxAI.MiniMax M2.5
Minimax · DevQuasar
Params229B
Context192K
Q4_K_M138.3 GB
ReasoningTool use
QW
Qwen.Qwen2.5 3B Instruct
Qwen · DevQuasar
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
QW
nvidia.Qwen3 Nemotron 32B RLBFF
Qwen · DevQuasar
Params32.8B
Context40K
Q4_K_M19.8 GB
ReasoningTool use
CO
CohereLabs.c4ai Command R v01
Command R · DevQuasar
Params35B
Context128K
Q4_K_M21.5 GB
GGUF
QW
Qwen.Qwen3Guard Gen 4B
Qwen · DevQuasar
Params4.41B
Context32K
Q4_K_M2.7 GB
Reasoning
GL
Zai org.GLM 4.5 Air
GLM · DevQuasar
Params110B
Context128K
Q4_K_M72.9 GB
ReasoningTool use
MI
cerebras/MiniMax-M2-REAP-172B-A10B
Minimax · DevQuasar
Params173B
Context192K
Q4_K_M104.4 GB
ReasoningTool use
QW
Qwen.Qwen2.5 7B
Qwen · DevQuasar
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
CO
CohereLabs.command A Reasoning 08 2025
Command · DevQuasar
Params111B
Context488K
Q4_K_M67.1 GB
ReasoningTool use
ME
Google.Medgemma 27b Text It
Medgemma · DevQuasar
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
TR
Arcee ai.Trinity Large Preview
Trinity · DevQuasar
Params399B
Context256K
Q4_K_M239.6 GB
Tool use

Keep browsing