Quantization publisher
Frosty40
Frosty40 publishes 1 quantizations across 1 models in our index, averaging 4.514 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
4.514
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Leanstral-1.5-119B-A6B | 1 | 62.52 GiB |