GGUF models by bau0221
39 GGUF models quantized by bau0221 on Hugging Face. Sizes run from 1.24B to 3.82B parameters. The longest trained context is 128K tokens.
About bau0221 on Hugging Face
bau0221 has published 39 GGUF models that ggufmodels.com tracks, across families such as Llama, Model and Hli. The most downloaded are model 1210, model 1210 llama 3 and model 1210 llama.
The quants bau0221 publishes most often are Q8_0 (29), Q4_K_M (5), F16 (2) and Q3_K_M (1). Their Q4_K_M files range from 0.8 to 2.3 GB. Parameter counts run from 1.24B to 3.82B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has bau0221 published?
39 models are listed here, mainly from the Llama, Model and Hli families. The most downloaded is model 1210.
Which quants does bau0221 publish?
The most common are Q8_0 (29 models), Q4_K_M (5 models), F16 (2 models) and Q3_K_M (1 models).