Quantization publisher
paragon-of-brah
paragon-of-brah publishes 4 quantizations across 1 models in our index, averaging 2.961 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
1
Quantizations
4
Models covered
1
Avg effective bpw
2.961
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | paragon-of-brah | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Nex-N2-Pro | IQ3_XXS | 147.24 GiB | tarruda | 116.31 GiB | +26.6% |
| Nex-N2-Pro | IQ2_M | 132.87 GiB | bartowski | 123.99 GiB | +7.2% |
| Nex-N2-Pro | IQ3_XXS | 147.24 GiB | bartowski | 154.67 GiB | -4.8% |
| Nex-N2-Pro | IQ1_M | 90.02 GiB | bartowski | 85.09 GiB | +5.8% |
| Nex-N2-Pro | IQ3_M | 176.93 GiB | bartowski | 176.54 GiB | +0.2% |
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 |
|---|---|---|
| Nex-N2-Pro | 4 | 90.02 GiB |