GGUF models by Felladrin
267 GGUF models quantized by Felladrin on Hugging Face. Sizes run from 23M to 229B parameters. The longest trained context is 1024K tokens.
About Felladrin on Hugging Face
Felladrin has published 267 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and OLMo. The most downloaded are SmolLM 360M, gguf pythia 1.4b sft full and gguf SmolLM 135M Instruct.
The quants Felladrin publishes most often are Q8_0 (122), Q5_K_M (107), Q6_K (98) and Q4_K_S (85). Their Q4_K_M files range from 0.0 to 129.4 GB. Parameter counts run from 23M to 229B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has Felladrin published?
267 models are listed here, mainly from the Qwen, Llama and OLMo families. The most downloaded is SmolLM 360M.
Which quants does Felladrin publish?
The most common are Q8_0 (122 models), Q5_K_M (107 models), Q6_K (98 models) and Q4_K_S (85 models).