GGUF models by adamksn
34 GGUF models quantized by adamksn on Hugging Face. Sizes run from 7.24B to 12.9B parameters. The longest trained context is 128K tokens.
About adamksn on Hugging Face
adamksn has published 34 GGUF models that ggufmodels.com tracks, across families such as Llama, Mistral and Zysec. The most downloaded are Mistral 7B Sunda v1.0, Pastiche Crown Clown 7B dare and NeuralMaxime 7B slerp.
The quants adamksn publishes most often are Q8_0 (34), Q6_K (34), Q4_0 (34) and Q5_K_M (23). Their Q4_K_M files range from 4.4 to 7.8 GB. Parameter counts run from 7.24B to 12.9B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has adamksn published?
34 models are listed here, mainly from the Llama, Mistral and Zysec families. The most downloaded is Mistral 7B Sunda v1.0.
Which quants does adamksn publish?
The most common are Q8_0 (34 models), Q6_K (34 models), Q4_0 (34 models) and Q5_K_M (23 models).