Quantization publisher
HDiffusion
HDiffusion publishes 3 quantizations across 1 models in our index, averaging 10.076 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
10.076
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | HDiffusion | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen3-VL-8B-NSFW-Caption-V4 | Q5_K_M | 5.45 GiB | mradermacher | 5.45 GiB | -0.0% |
| Qwen3-VL-8B-NSFW-Caption-V4 | Q8_0 | 8.11 GiB | mradermacher | 8.11 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 |
|---|---|---|
| Qwen3-VL-8B-NSFW-Caption-V4 | 3 | 5.45 GiB |