Quantization publisher

tarruda

tarruda publishes 1 quantizations across 1 models in our index, averaging 2.518 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
1
Models covered
1
Avg effective bpw
2.518
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuanttarrudavsTheirsDifference
Nex-N2-ProIQ3_XXS116.31 GiBbartowski154.67 GiB-24.8%
Nex-N2-ProIQ3_XXS116.31 GiBparagon-of-brah147.24 GiB-21.0%

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

ModelQuantizationsSmallest
Nex-N2-Pro1116.31 GiB