GGUF models by second-state
291 GGUF models quantized by second-state on Hugging Face. Sizes run from 23M to 236B parameters. The longest trained context is 10240K tokens.
About second-state on Hugging Face
second-state has published 291 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Mistral. The most downloaded are all-MiniLM-L6-v2, stable diffusion v1 5 and stable diffusion 3.5 large.
The quants second-state publishes most often are Q4_0 (288), Q5_0 (287), Q8_0 (285) and Q2_K (281). Their Q4_K_M files range from 0.0 to 142.5 GB. Parameter counts run from 23M to 236B, and the longest trained context window is 10240K tokens.
Frequently asked questions
What GGUF models has second-state published?
291 models are listed here, mainly from the Qwen, Llama and Mistral families. The most downloaded is all-MiniLM-L6-v2.
Which quants does second-state publish?
The most common are Q4_0 (288 models), Q5_0 (287 models), Q8_0 (285 models) and Q2_K (281 models).