Quantization publisher
dayuadg
dayuadg publishes 12 quantizations across 1 models in our index, averaging 5.822 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
1
Quantizations
12
Models covered
1
Avg effective bpw
5.822
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | dayuadg | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwen3.6-35B-A3B | Q8_0 | 35.21 GiB | Jackrong | 34.37 GiB | +2.4% |
| Qwen3.6-35B-A3B | Q6_K | 27.20 GiB | Jackrong | 26.56 GiB | +2.4% |
| Qwen3.6-35B-A3B | Q5_K_M | 23.61 GiB | Jackrong | 23.03 GiB | +2.5% |
| Qwen3.6-35B-A3B | Q4_K_M | 20.22 GiB | Jackrong | 19.71 GiB | +2.6% |
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 |
|---|---|---|
| Qwen3.6-35B-A3B | 12 | 12.34 GiB |