Quantization publisher

babycommando

babycommando publishes 4 quantizations across 1 models in our index, averaging 6.295 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
4
Models covered
1
Avg effective bpw
6.295
across their files

Models they publish

ModelQuantizationsSmallest
llama-3-8b-bnb-4bit43.41 GiB