GGUF models by YorkieOH10
82 GGUF models quantized by YorkieOH10 on Hugging Face. Sizes run from 134M to 46.7B parameters. The longest trained context is 1024K tokens.
About YorkieOH10 on Hugging Face
YorkieOH10 has published 82 GGUF models that ggufmodels.com tracks, across families such as Llama, Phi and Granite. The most downloaded are Meta Llama 3.1 8B Instruct Hf, Meta Llama 3.1 8B Instruct and Nomic Embed Text v1.5.
The quants YorkieOH10 publishes most often are Q8_0 (53), Q4_K_M (17), Q5_K_M (3) and Q6_K (1). Their Q4_K_M files range from 2.4 to 28.4 GB. Parameter counts run from 134M to 46.7B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has YorkieOH10 published?
82 models are listed here, mainly from the Llama, Phi and Granite families. The most downloaded is Meta Llama 3.1 8B Instruct Hf.
Which quants does YorkieOH10 publish?
The most common are Q8_0 (53 models), Q4_K_M (17 models), Q5_K_M (3 models) and Q6_K (1 models).