Quantization publisher
GrEarl
GrEarl publishes 2 quantizations across 1 models in our index, averaging 2.152 effective bits per weight.
From the file· summed file bytes
Repositories
2
Quantizations
2
Models covered
1
Avg effective bpw
2.152
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Kimi-K3 | 2 | 528.03 GiB |