Quantization publisher
densenet
densenet publishes 6 quantizations across 1 models in our index, averaging 5.566 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
6
Models covered
1
Avg effective bpw
5.566
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | densenet | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Gemma-4-31B-StyleTune | IQ2_S | 9.01 GiB | bartowski | 11.81 GiB | -23.7% |
| Gemma-4-31B-StyleTune | IQ4_NL | 16.09 GiB | bartowski | 17.53 GiB | -8.2% |
| Gemma-4-31B-StyleTune | IQ3_XXS | 11.74 GiB | bartowski | 12.65 GiB | -7.2% |
| Gemma-4-31B-StyleTune | BF16 | 59.82 GiB | bartowski | 59.82 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-StyleTune | 6 | 9.01 GiB |