Quantization publisher
Vegss
Vegss publishes 13 quantizations across 2 models in our index, averaging 6.206 effective bits per weight.
From the file· summed file bytes
Repositories
2
Quantizations
13
Models covered
2
Avg effective bpw
6.206
across their files
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| gemma-4-12b-it-uncensored | 8 | 4.50 GiB |
| Qwen3.6-14B-A3B-VibeForged-v2 | 5 | 4.96 GiB |