Quantization publisher
tensorart
tensorart publishes 2 quantizations across 1 models in our index, averaging 7.520 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
2
Models covered
1
Avg effective bpw
7.520
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| stable-diffusion-3.5-medium | 2 | 1.66 GiB |