Quantization publisher
Nekochu
Nekochu publishes 1 quantizations across 1 models in our index, averaging 5.347 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
5.347
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| gemma-4-31B-it | 1 | 20.35 GiB |