Quantization publisher
h34v7
h34v7 publishes 1 quantizations across 1 models in our index, averaging 4.919 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
4.919
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| DeepSeek-R1-Distill-Qwen-7B-Uncensored-Reasoner | 1 | 4.36 GiB |