Quantization publisher

impactframes

impactframes publishes 1 quantizations across 1 models in our index, averaging 5.561 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
5.561
across their files

Models they publish

ModelQuantizationsSmallest
llama-3-8b-bnb-4bit15.34 GiB