GGUF models by ZeroWw
204 GGUF models quantized by ZeroWw on Hugging Face. Sizes run from 268M to 15.7B parameters. The longest trained context is 1024K tokens.
About ZeroWw on Hugging Face
ZeroWw has published 204 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Gemma. The most downloaded are MiMo V2.6 Distill Qwen 9B, Meta Llama 3.1 8B Instruct Abliterated and Phi 3 medium 128k instruct.
The quants ZeroWw publishes most often are Q6_K (164), Q5_K (164), F16 (164) and Q8_0 (163). Parameter counts run from 268M to 15.7B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has ZeroWw published?
204 models are listed here, mainly from the Llama, Qwen and Gemma families. The most downloaded is MiMo V2.6 Distill Qwen 9B.
Which quants does ZeroWw publish?
The most common are Q6_K (164 models), Q5_K (164 models), F16 (164 models) and Q8_0 (163 models).