Quantization publisher
cusiman
cusiman publishes 3 quantizations across 1 models in our index, averaging 4.439 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
4.439
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | cusiman | vs | Theirs | Difference |
|---|---|---|---|---|---|
| FireRed-Image-Edit-1.1 | Q4_1 | 11.96 GiB | vantagewithai | 12.03 GiB | -0.5% |
| FireRed-Image-Edit-1.1 | Q4_K_M | 12.17 GiB | vantagewithai | 12.21 GiB | -0.3% |
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 |
|---|---|---|
| FireRed-Image-Edit-1.1 | 3 | 7.54 GiB |