GGUF models by NonMiFrega
38 GGUF models quantized by NonMiFrega on Hugging Face. Sizes run from 438M to 12.9B parameters. The longest trained context is 1024K tokens.
About NonMiFrega on Hugging Face
NonMiFrega has published 38 GGUF models that ggufmodels.com tracks, across families such as Apertus, Mistral and SmolLM. The most downloaded are DeepSeek R1 Distill Qwen 1.5B, DeepSeek R1 Distill Llama 8B and DeepSeek R1 0528 Qwen3 8B.
The quants NonMiFrega publishes most often are Q4_K_M (31) and Q8_0 (7). Their Q4_K_M files range from 0.3 to 7.8 GB. Parameter counts run from 438M to 12.9B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has NonMiFrega published?
38 models are listed here, mainly from the Apertus, Mistral and SmolLM families. The most downloaded is DeepSeek R1 Distill Qwen 1.5B.
Which quants does NonMiFrega publish?
The most common are Q4_K_M (31 models) and Q8_0 (7 models).