GGUF models by antoste
48 GGUF models quantized by antoste on Hugging Face. Sizes run from 134M to 18.5B parameters. The longest trained context is 1024K tokens.
About antoste on Hugging Face
antoste has published 48 GGUF models that ggufmodels.com tracks, across families such as Qwen, Phi and Llama. The most downloaded are Qwen2 1.5B Instruct, EuroLLM 1.7B Instruct Q4 K M and Qwen2 1.5B Instruct.
The quants antoste publishes most often are Q2_K (10), Q4_K_M (8), Q8_0 (6) and Q4_0 (4). Their Q4_K_M files range from 1.0 to 11.2 GB. Parameter counts run from 134M to 18.5B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has antoste published?
48 models are listed here, mainly from the Qwen, Phi and Llama families. The most downloaded is Qwen2 1.5B Instruct.
Which quants does antoste publish?
The most common are Q2_K (10 models), Q4_K_M (8 models), Q8_0 (6 models) and Q4_0 (4 models).