Quantization publisher
Serveurperso
Serveurperso publishes 13 quantizations across 3 models in our index, averaging 13.970 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 1 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
3
Quantizations
13
Models covered
3
Avg effective bpw
13.970
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Serveurperso | vs | Theirs | Difference |
|---|---|---|---|---|---|
| OmniVoice | Q8_0 | 0.88 GiB | cstr | 1.06 GiB | -16.9% |
A quantization label describes a target, not a recipe. Publishers make different choices about which tensors to keep at higher precision, and some apply an importance matrix while others don't — so two files both honestly labelled the same thing can differ measurably in size and in quality.
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Ace-Step1.5 | 5 | 19.22 GiB |
| Qwen3-TTS-12Hz-0.6B-Base | 4 | 4.72 GiB |
| OmniVoice | 4 | 0.61 GiB |