GGUF models by mrutkows
63 GGUF models quantized by mrutkows on Hugging Face. Sizes run from 30M to 117B parameters. The longest trained context is 1024K tokens.
About mrutkows on Hugging Face
mrutkows has published 63 GGUF models that ggufmodels.com tracks, across families such as Granite and gpt-oss. The most downloaded are Granite 3.3 8b Instruct, Granite Guardian 4.1 8b and Granite 3.3 2b Base.
The quants mrutkows publishes most often are Q8_0 (60), Q4_K_M (60), F16 (52) and Q6_K (46). Their Q4_K_M files range from 0.0 to 87.9 GB. Parameter counts run from 30M to 117B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has mrutkows published?
63 models are listed here, mainly from the Granite and gpt-oss families. The most downloaded is Granite 3.3 8b Instruct.
Which quants does mrutkows publish?
The most common are Q8_0 (60 models), Q4_K_M (60 models), F16 (52 models) and Q6_K (46 models).