Quantization publisher
katafiek
katafiek publishes 4 quantizations across 1 models in our index, averaging 6.474 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 4 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
6.474
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | katafiek | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Katarau-9B-ru-RP-nsfw | Q4_K_M | 5.24 GiB | mradermacher | 5.24 GiB | -0.0% |
| Katarau-9B-ru-RP-nsfw | Q5_K_M | 6.02 GiB | mradermacher | 6.02 GiB | -0.0% |
| Katarau-9B-ru-RP-nsfw | Q6_K | 6.85 GiB | mradermacher | 6.85 GiB | -0.0% |
| Katarau-9B-ru-RP-nsfw | Q8_0 | 8.87 GiB | mradermacher | 8.87 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 |
|---|---|---|
| Katarau-9B-ru-RP-nsfw | 4 | 5.24 GiB |