Quantization publisher
glogwa68
glogwa68 publishes 3 quantizations across 1 models in our index, averaging 14.348 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
14.348
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Llama-4-Scout-17B-16E-Instruct-4bit | 3 | 20.95 GiB |