Quantization publisher
muhtasham
muhtasham publishes 3 quantizations across 1 models in our index, averaging 6.215 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
6.215
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| qwen2.5-7b-bnb-4bit | 3 | 4.36 GiB |