Quantization publisher
r1r21nb
r1r21nb publishes 1 quantizations across 1 models in our index, averaging 5.003 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
5.003
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Qwen2.5-3B-Instruct | 1 | 1.80 GiB |