Quantization publisher
Naphula
Naphula publishes 32 quantizations across 4 models in our index, averaging 4.488 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 3 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
4
Quantizations
32
Models covered
4
Avg effective bpw
4.488
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Naphula | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA | Q8_0 | 25.02 GiB | mradermacher | 25.02 GiB | -0.0% |
| Slimaki-Tavern-24B-v1.3 | Q8_0 | 23.33 GiB | mradermacher | 23.33 GiB | -0.0% |
| Slimaki-Tavern-24B-v1.3 | Q5_K_M | 15.61 GiB | mradermacher | 15.61 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 |
|---|---|---|
| Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA | 1 | 25.02 GiB |
| Slimaki-Tavern-24B-v1.3 | 3 | 12.52 GiB |
| KrakenSakura-Maelstrom-12B-v1 | 19 | 2.79 GiB |
| Morax-24B-v2 | 9 | 6.10 GiB |