GGUF models by steampunque

73 GGUF models quantized by steampunque on Hugging Face. Sizes run from 1.17B to 120B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
Ministral 3 8B Instruct 2512
Mistral · steampunque
Params8.49B
Context256K
Smallest5.3 GB
Tool useVision
QW
Qwen2.5 VL 32B Instruct
Qwen · steampunque
Params32.8B
Context125K
Smallest18.0 GB
Vision
HY
HY MT2 7B
steampunque
Params7.5B
Context256K
Smallest6.0 GB
GGUF
QW
Qwen3 VL 30B A3B Instruct
Qwen · steampunque
Params30.5B
Context256K
Smallest16.9 GB
Tool useVision
QW
Qwen3 14B
Qwen · steampunque
Params14.8B
Context40K
Smallest8.5 GB
ReasoningTool use
GE
Gemma 4 E4B It
Gemma · steampunque
Params7.52B
Context128K
Smallest6.3 GB
ReasoningTool useVision
QW
Qwen3 4B
Qwen · steampunque
Params4.02B
Context40K
Smallest3.6 GB
ReasoningTool use
RI
Ring Mini 2.0
Ring · steampunque
Params16.3B
Context32K
Smallest13.2 GB
Reasoning
QW
Qwen3 30B A3B
Qwen · steampunque
Params30.5B
Context40K
Smallest17.8 GB
ReasoningTool use
DE
Deepseek R1 Distill Qwen 7B
DeepSeek · steampunque
Params7.62B
Context128K
Smallest6.2 GB
ReasoningTool use
QW
QwQ 32B
Qwen · steampunque
Params32.8B
Context128K
Smallest17.9 GB
ReasoningTool use
QW
Qwen2.5 Coder 32B Instruct
Qwen · steampunque
Params32.8B
Context32K
Smallest19.4 GB
CodingTool use
QW
Qwen3 32B
Qwen · steampunque
Params32.8B
Context40K
Smallest18.5 GB
ReasoningTool use

Keep browsing