GGUF models by yamatazen
46 GGUF models quantized by yamatazen on Hugging Face. Sizes run from 4.02B to 23.6B parameters. The longest trained context is 1000K tokens.
About yamatazen on Hugging Face
yamatazen has published 46 GGUF models that ggufmodels.com tracks, across families such as Etherealaurora, Qwen and Himeyuri. The most downloaded are Gemma2 Snowflakes 9B, Qwen3 4B Instruct 2507 Heretic and Shisa v2 Mistral Nemo 12B Abliterated.
The quants yamatazen publishes most often are Q4_K_M (45) and Q3_K_M (1). Their Q4_K_M files range from 2.5 to 12.4 GB. Parameter counts run from 4.02B to 23.6B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has yamatazen published?
46 models are listed here, mainly from the Etherealaurora, Qwen and Himeyuri families. The most downloaded is Gemma2 Snowflakes 9B.
Which quants does yamatazen publish?
The most common are Q4_K_M (45 models) and Q3_K_M (1 models).