Quantization publisher
intellectlabs
intellectlabs publishes 8 quantizations across 1 models in our index, averaging 13.745 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
8
Models covered
1
Avg effective bpw
13.745
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Kepler-8B-Instruct-v2 | 8 | 5.61 GiB |