Quantization publisher
wangzhang
wangzhang publishes 10 quantizations across 3 models in our index, averaging 9.733 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
3
Quantizations
10
Models covered
3
Avg effective bpw
9.733
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | wangzhang | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-31B-it-abliterated | Q5_K_M | 20.35 GiB | mradermacher | 20.35 GiB | 0.0% |
| gemma-4-31B-it-abliterated | Q8_0 | 30.39 GiB | mradermacher | 30.39 GiB | 0.0% |
| Qwen3.6-27B-abliterated | Q4_K_M | 15.41 GiB | mradermacher | 15.41 GiB | -0.0% |
| Qwen3.6-27B-abliterated | Q8_0 | 26.63 GiB | mradermacher | 26.63 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-it-abliterated | 4 | 20.35 GiB |
| gemma-4-26B-A4B-it-abliterix | 3 | 15.64 GiB |
| Qwen3.6-27B-abliterated | 3 | 15.41 GiB |