GGUF models by theprint
136 GGUF models quantized by theprint on Hugging Face. Sizes run from 436M to 18B parameters. The longest trained context is 1000K tokens.
About theprint on Hugging Face
theprint has published 136 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Gemma. The most downloaded are CreativeWriter Llama3.2 3B, DoItYourself v1 2B and Llama3.2 3B Explained.
The quants theprint publishes most often are Q8_0 (133), Q4_K_M (132), Q6_K (128) and Q5_K_M (127). Their Q4_K_M files range from 0.4 to 11.1 GB. Parameter counts run from 436M to 18B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has theprint published?
136 models are listed here, mainly from the Llama, Qwen and Gemma families. The most downloaded is CreativeWriter Llama3.2 3B.
Which quants does theprint publish?
The most common are Q8_0 (133 models), Q4_K_M (132 models), Q6_K (128 models) and Q5_K_M (127 models).