Quantization publisher
mozilla-ai
mozilla-ai publishes 1 quantizations across 1 models in our index, averaging 16.001 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
16.001
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Mistral-7B-Instruct-v0.2 | 1 | 13.49 GiB |