Quantization publisher
glebkudr
glebkudr publishes 1 quantizations across 1 models in our index, averaging 8.409 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
8.409
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Infinity-Parser2-Pro | 1 | 34.37 GiB |