Quantization publisher
GeorgyGUF
GeorgyGUF publishes 1 quantizations across 1 models in our index, averaging 1.981 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
1.981
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Llama-4-Maverick-17B-128E-Instruct | 1 | 92.59 GiB |