GGUF models by ClaudioItaly
172 GGUF models quantized by ClaudioItaly on Hugging Face. Sizes run from 51M to 32.8B parameters. The longest trained context is 1000K tokens.
About ClaudioItaly on Hugging Face
ClaudioItaly has published 172 GGUF models that ggufmodels.com tracks, across families such as Qwen, Intelligence and Evolutionstory. The most downloaded are Hermes 3 Llama 3.1 8B, Qwen2.5 Coder 7B Instruct and DeepSeek R1 Distill Qwen 7B.
The quants ClaudioItaly publishes most often are Q4_K_M (80), Q5_K_M (50), Q6_K (19) and Q8_0 (9). Their Q4_K_M files range from 4.1 to 9.0 GB. Parameter counts run from 51M to 32.8B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has ClaudioItaly published?
172 models are listed here, mainly from the Qwen, Intelligence and Evolutionstory families. The most downloaded is Hermes 3 Llama 3.1 8B.
Which quants does ClaudioItaly publish?
The most common are Q4_K_M (80 models), Q5_K_M (50 models), Q6_K (19 models) and Q8_0 (9 models).