Quantization publisher
Cordux
Cordux publishes 1 quantizations across 1 models in our index, averaging 4.713 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
4.713
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Qwen3-4B-abliterated | 1 | 2.21 GiB |