Quantization publisher
MRockatansky
MRockatansky publishes 15 quantizations across 5 models in our index, averaging 8.552 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 7 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
5
Quantizations
15
Models covered
5
Avg effective bpw
8.552
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | MRockatansky | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-31B-Mergemaxxed | IQ4_XS | 15.59 GiB | mradermacher | 15.70 GiB | -0.7% |
| gemma-4-31B-anthology | IQ4_XS | 15.59 GiB | mradermacher | 15.70 GiB | -0.7% |
| gemma-4-31B-anthology | Q4_K_M | 17.40 GiB | mradermacher | 17.40 GiB | -0.0% |
| gemma-4-31B-anthology | Q5_K_S | 19.85 GiB | mradermacher | 19.85 GiB | -0.0% |
| Cogidonia-v2-24B | IQ4_XS | 12.00 GiB | mradermacher | 12.00 GiB | -0.0% |
| Cogidonia-v2-24B | Q4_K_M | 13.35 GiB | mradermacher | 13.35 GiB | -0.0% |
| Cogidonia-v2-24B | Q6_K | 18.02 GiB | mradermacher | 18.02 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 |
|---|---|---|
| gemma-4-31B-anthology | 5 | 15.59 GiB |
| gemma-4-31B-Mergemaxxed | 3 | 15.59 GiB |
| Cogidonia-v2-24B | 4 | 12.00 GiB |
| Gemma-4-31B-Storymaxxed3 | 2 | 17.72 GiB |
| Gemma-4-31B-storymaxxed2 | 1 | 57.20 GiB |