GGUF models by NikolayKozloff
1011 GGUF models quantized by NikolayKozloff on Hugging Face. Sizes run from 30M to 33.1B parameters. The longest trained context is 1024K tokens.
About NikolayKozloff on Hugging Face
NikolayKozloff has published 1,011 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Mistral. The most downloaded are Translategemma 12b It, Translategemma 12b It and Translategemma 4b It.
The quants NikolayKozloff publishes most often are Q8_0 (523), Q6_K (92), Q5_K_S (73) and Q5_K_M (68). Their Q4_K_M files range from 3.7 to 19.9 GB. Parameter counts run from 30M to 33.1B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has NikolayKozloff published?
1,011 models are listed here, mainly from the Llama, Qwen and Mistral families. The most downloaded is Translategemma 12b It.
Which quants does NikolayKozloff publish?
The most common are Q8_0 (523 models), Q6_K (92 models), Q5_K_S (73 models) and Q5_K_M (68 models).