Quantization publisher
HeYujie
HeYujie publishes 10 quantizations across 1 models in our index, averaging 4.841 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 8 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
10
Models covered
1
Avg effective bpw
4.841
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | HeYujie | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Huihui-Qwen3.5-35B-A3B-abliterated | Q2_K | 11.94 GiB | mradermacher | 11.94 GiB | -0.0% |
| Huihui-Qwen3.5-35B-A3B-abliterated | Q3_K_M | 15.61 GiB | mradermacher | 15.61 GiB | -0.0% |
| Huihui-Qwen3.5-35B-A3B-abliterated | Q3_K_S | 14.14 GiB | mradermacher | 14.14 GiB | -0.0% |
| Huihui-Qwen3.5-35B-A3B-abliterated | Q4_K_M | 19.72 GiB | mradermacher | 19.72 GiB | -0.0% |
| Huihui-Qwen3.5-35B-A3B-abliterated | Q4_K_S | 18.52 GiB | mradermacher | 18.52 GiB | -0.0% |
| Huihui-Qwen3.5-35B-A3B-abliterated | Q5_K_M | 23.06 GiB | mradermacher | 23.06 GiB | -0.0% |
| Huihui-Qwen3.5-35B-A3B-abliterated | Q6_K | 26.56 GiB | mradermacher | 26.56 GiB | -0.0% |
| Huihui-Qwen3.5-35B-A3B-abliterated | Q8_0 | 34.37 GiB | mradermacher | 34.37 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 |
|---|---|---|
| Huihui-Qwen3.5-35B-A3B-abliterated | 10 | 11.94 GiB |