GGUF models by kenonix
69 GGUF models quantized by kenonix on Hugging Face. Sizes run from 7M to 26.9B parameters. The longest trained context is 256K tokens.
About kenonix on Hugging Face
kenonix has published 69 GGUF models that ggufmodels.com tracks, across families such as Gemma, Llama and Next. The most downloaded are Phi 4 Mini Instruct, Llama 3.3 8B Thinking Gemini Flash 11000x 128k and Llama 3.3 8B Thinking Gemini Flash 11000x 128k.
The quants kenonix publishes most often are Q8_0 (35), Q4_K_M (18), Q6_K (6) and Q4_0 (3). Their Q4_K_M files range from 0.8 to 16.5 GB. Parameter counts run from 7M to 26.9B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has kenonix published?
69 models are listed here, mainly from the Gemma, Llama and Next families. The most downloaded is Phi 4 Mini Instruct.
Which quants does kenonix publish?
The most common are Q8_0 (35 models), Q4_K_M (18 models), Q6_K (6 models) and Q4_0 (3 models).