Quantization publisher
Guilherme34
Guilherme34 publishes 27 quantizations across 1 models in our index, averaging 5.681 effective bits per weight.
From the file· summed file bytes
Repositories
2
Quantizations
27
Models covered
1
Avg effective bpw
5.681
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Firefly-v4 | 27 | 2.78 GiB |