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
QW
Qwen3 Omni 30B A3B Instruct
Qwen · steampunque
Params30.5B
Context64K
Smallest16.9 GB
ReasoningTool useVision
GL
GLM 4.5 Air
GLM · steampunque
Params120B
Context128K
Smallest63.6 GB
ReasoningTool use
QW
Qwen3.5 35B A3B
Qwen · steampunque
Params35.5B
Context256K
Smallest21.8 GB
ReasoningTool useVision
LL
Llama 4 Scout 17B 16E Instruct
Llama · steampunque
Params108B
Context10240K
Smallest42.8 GB
Tool use
QW
Qwen3.5 4B
Qwen · steampunque
Params4.21B
Context256K
Smallest3.3 GB
ReasoningTool useVision
GE
Gemma 4 26B A4B It
Gemma · steampunque
Params25.2B
Context256K
Smallest16.1 GB
ReasoningTool useVision
QW
Qwen3 Coder 30B A3B Instruct
Qwen · steampunque
Params30.5B
Context256K
Smallest18.3 GB
CodingTool use
QW
Qwen3.5 27B
Qwen · steampunque
Params27.3B
Context256K
Smallest16.7 GB
ReasoningTool useVision
GE
Gemma 4 31B It
Gemma · steampunque
Params30.7B
Context256K
Smallest17.6 GB
ReasoningTool useVision
QW
Qwen3 8B
Qwen · steampunque
Params8.19B
Context40K
Smallest5.0 GB
ReasoningTool use
TR
Translategemma 12b It
Translategemma · steampunque
Params11.8B
Context128K
Smallest7.4 GB
Vision
QW
Qwen2.5 Omni 7B
Qwen · steampunque
Params7.62B
Context32K
Smallest4.8 GB
Vision
GL
GLM 4.6V Flash
GLM · steampunque
Params9.46B
Context128K
Smallest5.6 GB
ReasoningTool useVision
QW
Qwen3.5 9B
Qwen · steampunque
Params9.2B
Context256K
Smallest6.2 GB
ReasoningTool useVision
QW
Qwen3.6 35B A3B
Qwen · steampunque
Params35.5B
Context256K
Smallest21.8 GB
ReasoningTool useVision
MI
Mistral Small 3.1 24B Instruct 2503
Mistral · steampunque
Params23.6B
Context128K
Smallest9.8 GB
Vision
MI
Ministral 3 14B Instruct 2512 MP
Mistral · steampunque
Params13.5B
Context256K
Smallest8.3 GB
Tool useVision
MI
MiniCPM V 4 5 MP
MiniCPM · steampunque
Params8.19B
Context40K
Smallest5.2 GB
ReasoningTool useVision
GL
GLM Z1 9B 0414
GLM · steampunque
Params9.46B
Context32K
Smallest6.2 GB
Tool use
QW
Qwen2.5 VL 7B Instruct
Qwen · steampunque
Params7.62B
Context125K
Smallest4.8 GB
Vision
GL
GLM Z1 32B 0414
GLM · steampunque
Params32.6B
Context32K
Smallest19.3 GB
Tool use
MI
Voxtral Mini 3B 2507
Mistral · steampunque
Params4.01B
Context128K
Smallest3.2 GB
Tool useVision
QW
Qwen3.8 27B
Qwen · steampunque
Params27.3B
Context256K
Smallest16.8 GB
ReasoningTool useVision
QW
Qwen2.5 VL 3B Instruct
Qwen · steampunque
Params3.09B
Context125K
Smallest2.0 GB
Vision
LL
ultravox v0 5 llama 3 1 8b MP
Llama · steampunque
Params8.03B
Context128K
Smallest6.0 GB
Tool useVision
GP
Gpt Oss 20b
gpt-oss · steampunque
Params20.9B
Context128K
Smallest12.4 GB
Tool use
LF
LFM2 VL 1.6B
Lfm · steampunque
Params1.17B
Context125K
Smallest1.1 GB
Vision
QW
Qwen3 VL 8B Instruct
Qwen · steampunque
Params8.19B
Context256K
Smallest5.4 GB
Tool useVision
MI
Mistral Small 3.2 24B Instruct 2506
Mistral · steampunque
Params23.6B
Context128K
Smallest12.7 GB
Vision
GE
Gemma 3 27b It
Gemma · steampunque
Params27B
Context128K
Smallest15.8 GB
Vision

About steampunque on Hugging Face

steampunque has published 73 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Mistral. The most downloaded are Qwen3 Omni 30B A3B Instruct, GLM 4.5 Air and Qwen3.5 35B A3B.

The quants steampunque publishes most often are Q4_K (34), Q6_K (26), Q8_0 (5) and Q3_K (3). Parameter counts run from 1.17B to 120B, and the longest trained context window is 10240K tokens.

Frequently asked questions

What GGUF models has steampunque published?

73 models are listed here, mainly from the Qwen, Gemma and Mistral families. The most downloaded is Qwen3 Omni 30B A3B Instruct.

Which quants does steampunque publish?

The most common are Q4_K (34 models), Q6_K (26 models), Q8_0 (5 models) and Q3_K (3 models).

Keep browsing