Quantization publisher
culturerevolt
culturerevolt publishes 6 quantizations across 1 models in our index, averaging 5.607 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
6
Models covered
1
Avg effective bpw
5.607
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | culturerevolt | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-12b-heretic-abliterated | IQ4_XS | 6.18 GiB | mradermacher | 6.23 GiB | -0.8% |
| gemma-4-12b-heretic-abliterated | Q8_0 | 11.80 GiB | mradermacher | 11.80 GiB | -0.0% |
| gemma-4-12b-heretic-abliterated | Q4_K_M | 6.87 GiB | mradermacher | 6.87 GiB | 0.0% |
| gemma-4-12b-heretic-abliterated | Q5_K_M | 7.96 GiB | mradermacher | 7.96 GiB | 0.0% |
| gemma-4-12b-heretic-abliterated | Q6_K | 9.11 GiB | mradermacher | 9.11 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-4-12b-heretic-abliterated | 6 | 4.91 GiB |