Quantization publisher

gbuzhf

gbuzhf publishes 3 quantizations across 1 models in our index, averaging 5.675 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
5.675
across their files

Models they publish

ModelQuantizationsSmallest
KAT-Coder-V2.5-Dev316.96 GiB