Quantization publisher

ysong21

ysong21 publishes 1 quantizations across 1 models in our index, averaging 6.109 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
6.109
across their files

Models they publish

ModelQuantizationsSmallest
gemma-4-12B-it-qat-q4_0-unquantized-assistant10.30 GiB