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
ModelQuantEmanuelOverridevsTheirsDifference
Melody1437-26B-A4B-v2.0Q6_K35.68 GiBReadyArt42.98 GiB-17.0%
Gemma-4-26B-A4B-StyleTune-V2Q4_K_M13.04 GiBmradermacher16.03 GiB-18.6%
Gemma-4-26B-A4B-StyleTune-V2Q3_K_M11.78 GiBmradermacher12.67 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

ModelQuantizationsSmallest
Melody1437-26B-A4B-v2.0311.49 GiB
Gemma-4-26B-A4B-StyleTune-V2311.78 GiB
gemma-4-19b-a4b-it-REAP-heretic38.48 GiB