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
| Model | Quant | FINAL-Bench | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Darwin-28B-Coder | Q4_K_M | 15.66 GiB | mradermacher | 15.66 GiB | -0.0% |
| Darwin-28B-Coder | Q8_0 | 27.05 GiB | mradermacher | 27.05 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
| Model | Quantizations | Smallest |
|---|---|---|
| Darwin-36B-Opus | 7 | 4.75 GiB |
| Ourbox-35B-JGOS | 4 | 7.67 GiB |
| Darwin-28B-Coder | 3 | 15.66 GiB |