Quantization publisher
maharshpatelx
maharshpatelx publishes 1 quantizations across 1 models in our index, averaging 4.927 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
1
Models covered
1
Avg effective bpw
4.927
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| deepseek-r1-distill-qwen-1.5b-unsloth-bnb-4bit | 1 | 1.04 GiB |