GGUF models by paul-stansifer
47 GGUF models quantized by paul-stansifer on Hugging Face. Sizes run from 54M to 13B parameters. The longest trained context is 128K tokens.
About paul-stansifer on Hugging Face
paul-stansifer has published 47 GGUF models that ggufmodels.com tracks, across families such as Mistral, Gemma and Llama. The most downloaded are qw us tinyllama 1b, qw3 smollm3 3b 1x2e 4 and qw3 llama2 7b 1x2e 4.
The quants paul-stansifer publishes most often are Q4_K_M (44), Q8_0 (23), Q2_K (21) and F16 (9). Their Q4_K_M files range from 1.1 to 5.8 GB. Parameter counts run from 54M to 13B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has paul-stansifer published?
47 models are listed here, mainly from the Mistral, Gemma and Llama families. The most downloaded is qw us tinyllama 1b.
Which quants does paul-stansifer publish?
The most common are Q4_K_M (44 models), Q8_0 (23 models), Q2_K (21 models) and F16 (9 models).