These are GGUF statis quants of: nbeerbower/llama-3-stinky-v2-8B

Original model link: https://huggingface.co/nbeerbower/llama-3-stinky-v2-8B

The quants have been tested and work propperly with the latest version of Koboldcpp.

Downloads last month
231
GGUF
Model size
8.03B params
Architecture
llama

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Inference API
Unable to determine this model's library. Check the docs .