GGUF models by s3nh
182 GGUF models quantized by s3nh on Hugging Face. Sizes run from 160M to 46.7B parameters. The longest trained context is 128K tokens.
About s3nh on Hugging Face
s3nh has published 182 GGUF models that ggufmodels.com tracks, across families such as Mistral, Llama and Utena. The most downloaded are NSFW-Panda-7B, AdaptLLM law LLM 13B and UTENA-7B-NSFW-V2.
The quants s3nh publishes most often are Q4_K_M (179), Q8_0 (168), Q6_K (168) and Q3_K_S (168). Their Q4_K_M files range from 0.7 to 28.4 GB. Parameter counts run from 160M to 46.7B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has s3nh published?
182 models are listed here, mainly from the Mistral, Llama and Utena families. The most downloaded is NSFW-Panda-7B.
Which quants does s3nh publish?
The most common are Q4_K_M (179 models), Q8_0 (168 models), Q6_K (168 models) and Q3_K_S (168 models).