Quantization publisher

terrorswift

terrorswift publishes 2 quantizations across 1 models in our index, averaging 11.658 effective bits per weight.

From the file· summed file bytes
Repositories
1
Quantizations
2
Models covered
1
Avg effective bpw
11.658
across their files

Models they publish

ModelQuantizationsSmallest
gemma-4-26B-A4B-it225.02 GiB