Quantization publisher
ZERO-POINT-AI
ZERO-POINT-AI publishes 5 quantizations across 1 models in our index, averaging 8.382 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
5
Models covered
1
Avg effective bpw
8.382
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Miss_MARTHA-9B-Qwen3.5-Omni | 5 | 5.24 GiB |