Quantization publisher
ai-sage
ai-sage publishes 4 quantizations across 1 models in our index, averaging 8.357 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
4
Models covered
1
Avg effective bpw
8.357
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| GigaChat3-10B-A1.8B-base | 4 | 6.03 GiB |