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.
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).