Quantization publisher
Amensia
Amensia publishes 1 quantizations across 1 models in our index, averaging 5.305 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
5.305
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| chatglm3-6b | 1 | 3.86 GiB |