Quantization publisher
duchao1210
duchao1210 publishes 1 quantizations across 1 models in our index, averaging 15.609 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
15.609
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| qwen2.5-3b-instruct-unsloth-bnb-4bit | 1 | 5.75 GiB |