Quantization publisher
douyamv
douyamv publishes 3 quantizations across 1 models in our index, averaging 5.680 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
3
Models covered
1
Avg effective bpw
5.680
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | douyamv | vs | Theirs | Difference |
|---|---|---|---|---|---|
| gemma-4-31B-it | Q4_K_M | 17.40 GiB | bartowski | 18.25 GiB | -4.7% |
| gemma-4-31B-it | Q3_K_M | 14.24 GiB | bartowski | 14.82 GiB | -4.0% |
| gemma-4-31B-it | Q3_K_M | 14.24 GiB | unsloth | 13.72 GiB | +3.7% |
| gemma-4-31B-it | Q8_0 | 30.39 GiB | bartowski | 30.87 GiB | -1.6% |
| gemma-4-31B-it | Q4_K_M | 17.40 GiB | unsloth | 17.07 GiB | +2.0% |
| gemma-4-31B-it | Q8_0 | 30.39 GiB | unsloth | 30.39 GiB | -0.0% |
| gemma-4-31B-it | Q4_K_M | 17.40 GiB | lmstudio-community | 17.40 GiB | -0.0% |
| gemma-4-31B-it | Q8_0 | 30.39 GiB | lmstudio-community | 30.39 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 | 3 | 14.24 GiB |