Quantization publisher
kvaer
kvaer publishes 15 quantizations across 1 models in our index, averaging 5.880 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
15
Models covered
1
Avg effective bpw
5.880
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Mistral-Nemo-Base-2407 | 15 | 4.46 GiB |