Quantization publisher

dhruvsangani

dhruvsangani publishes 1 quantizations across 1 models in our index, averaging 4.772 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
4.772
across their files

Models they publish

ModelQuantizationsSmallest
meta-llama-3.1-8b-instruct-bnb-4bit14.58 GiB