Quantization publisher
Olak17
Olak17 publishes 24 quantizations across 1 models in our index, averaging 4.115 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
24
Models covered
1
Avg effective bpw
4.115
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Qwen2.5-Coder-1.5B-Unsensored-DPO | 24 | 0.41 GiB |