Quantization publisher
EmanuelOverride
EmanuelOverride publishes 9 quantizations across 3 models in our index, averaging 6.581 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 3 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
3
Quantizations
9
Models covered
3
Avg effective bpw
6.581
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | EmanuelOverride | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Melody1437-26B-A4B-v2.0 | Q6_K | 35.68 GiB | ReadyArt | 42.98 GiB | -17.0% |
| Gemma-4-26B-A4B-StyleTune-V2 | Q4_K_M | 13.04 GiB | mradermacher | 16.03 GiB | -18.6% |
| Gemma-4-26B-A4B-StyleTune-V2 | Q3_K_M | 11.78 GiB | mradermacher | 12.67 GiB | -7.0% |
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 |
|---|---|---|
| Melody1437-26B-A4B-v2.0 | 3 | 11.49 GiB |
| Gemma-4-26B-A4B-StyleTune-V2 | 3 | 11.78 GiB |
| gemma-4-19b-a4b-it-REAP-heretic | 3 | 8.48 GiB |