Quantization publisher
AesSedai
AesSedai publishes 8 quantizations across 2 models in our index, averaging 3.478 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
2
Quantizations
8
Models covered
2
Avg effective bpw
3.478
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | AesSedai | vs | Theirs | Difference |
|---|---|---|---|---|---|
| MiMo-V2.5-Pro | IQ4_XS | 454.99 GiB | bartowski | 508.09 GiB | -10.5% |
| Kimi-K2.5 | IQ2_S | 311.72 GiB | bartowski | 264.31 GiB | +17.9% |
| Kimi-K2.5 | IQ2_XXS | 262.75 GiB | bartowski | 228.43 GiB | +15.0% |
| MiMo-V2.5-Pro | IQ2_S | 297.46 GiB | bartowski | 290.79 GiB | +2.3% |
| MiMo-V2.5-Pro | Q4_K_M | 585.99 GiB | bartowski | 580.09 GiB | +1.0% |
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 |
|---|---|---|
| Kimi-K2.5 | 3 | 262.75 GiB |
| MiMo-V2.5-Pro | 5 | 297.46 GiB |