Quantization publisher
gaianet
gaianet publishes 8 quantizations across 1 models in our index, averaging 5.191 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 6 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
8
Models covered
1
Avg effective bpw
5.191
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | gaianet | vs | Theirs | Difference |
|---|---|---|---|---|---|
| FLUX.1-Fill-dev | Q8_0 | 12.28 GiB | YarvixPA | 11.85 GiB | +3.6% |
| FLUX.1-Fill-dev | Q8_0 | 12.28 GiB | second-state | 11.96 GiB | +2.6% |
| FLUX.1-Fill-dev | Q4_1 | 7.14 GiB | YarvixPA | 7.03 GiB | +1.6% |
| FLUX.1-Fill-dev | Q5_0 | 7.83 GiB | YarvixPA | 7.72 GiB | +1.4% |
| FLUX.1-Fill-dev | Q5_1 | 8.52 GiB | YarvixPA | 8.41 GiB | +1.3% |
| FLUX.1-Fill-dev | Q4_0 | 6.45 GiB | YarvixPA | 6.34 GiB | +1.8% |
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 |
|---|---|---|
| FLUX.1-Fill-dev | 8 | 3.87 GiB |