Quantization publisher
migtissera
migtissera publishes 7 quantizations across 2 models in our index, averaging 7.767 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
2
Quantizations
7
Models covered
2
Avg effective bpw
7.767
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | migtissera | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Tess-4-27B | Q8_0 | 29.58 GiB | bartowski | 27.12 GiB | +9.1% |
| Tess-4-27B | Q6_K | 20.57 GiB | bartowski | 21.85 GiB | -5.9% |
| Tess-4-27B | Q4_K_M | 17.30 GiB | bartowski | 16.55 GiB | +4.5% |
| Tess-4-9B | Q6_K | 6.85 GiB | bartowski | 7.30 GiB | -6.1% |
| Tess-4-9B | Q4_K_M | 5.24 GiB | bartowski | 5.63 GiB | -6.9% |
| Tess-4-9B | Q8_0 | 8.87 GiB | bartowski | 9.13 GiB | -2.8% |
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 |
|---|---|---|
| Tess-4-27B | 3 | 17.30 GiB |
| Tess-4-9B | 4 | 5.24 GiB |