Quantization publisher
mattritchey
mattritchey publishes 1 quantizations across 1 models in our index, averaging 6.449 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
6.449
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| next-1b | 1 | 0.75 GiB |