Quantization publisher

FINAL-Bench

FINAL-Bench publishes 14 quantizations across 3 models in our index, averaging 4.491 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
4
Quantizations
14
Models covered
3
Avg effective bpw
4.491
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantFINAL-BenchvsTheirsDifference
Darwin-28B-CoderQ4_K_M15.66 GiBmradermacher15.66 GiB-0.0%
Darwin-28B-CoderQ8_027.05 GiBmradermacher27.05 GiB-0.0%

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
Darwin-36B-Opus74.75 GiB
Ourbox-35B-JGOS47.67 GiB
Darwin-28B-Coder315.66 GiB