Quantization publisher
Preyazz
Preyazz publishes 3 quantizations across 1 models in our index, averaging 3.853 effective bits per weight.
From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
3.853
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| DeepSeek-V4-Flash-Q8_0-GGUF | 3 | 96.19 GiB |