GGUF models by ubergarm

42 GGUF models quantized by ubergarm on Hugging Face. Sizes run from 10.7B to 1030B parameters. The longest trained context is 384K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 Coder 480B A35B Instruct
Qwen · ubergarm
Params480B
Context256K
Smallest116.7 GB
CodingTool use
QW
Qwen3 30B A3B
Qwen · ubergarm
Params30.5B
Context40K
Smallest19.0 GB
ReasoningTool use
MI
Devstral Small 2 24B Instruct 2512
Mistral · ubergarm
Params23.6B
Context384K
Smallest13.0 GB
CodingTool use
HU
Hunyuan A13B Instruct
Hunyuan · ubergarm
Params80.4B
Context256K
Smallest36.6 GB
ReasoningTool use
QW
Qwen3 235B A22B Thinking 2507
Qwen · ubergarm
Params235B
Context256K
Smallest87.9 GB
ReasoningTool use
MI
MiMo V2 Flash
Mimo · ubergarm
Params309B
Context256K
Smallest89.0 GB
ReasoningTool use
DE
DeepSeek R1T Chimera
DeepSeek · ubergarm
Params672B
Context160K
Smallest363.4 GB
ReasoningTool use
QW
Qwen3 235B A22B
Qwen · ubergarm
Params235B
Context40K
Smallest114.7 GB
ReasoningTool use
KI
Kimi Dev 72B
Kimi · ubergarm
Params72.7B
Context128K
Smallest34.7 GB
CodingTool use
MI
Devstral 2 123B Instruct 2512
Mistral · ubergarm
Params125B
Context256K
Smallest73.6 GB
CodingTool use
GE
Gemma 3 27b It Qat Q4_0 Unquantized
Gemma · ubergarm
Params27B
Context128K
Smallest13.7 GB
GGUF
QW
Qwen3 14B
Qwen · ubergarm
Params14.8B
Context40K
Smallest9.1 GB
ReasoningTool use

Keep browsing