Quantization publisher
kof1467
kof1467 publishes 1 quantizations across 1 models in our index, averaging 5.207 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
5.207
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| supergemma4-26b-abliterated-multimodal | 1 | 15.64 GiB |