Quantization publisher

majentik

majentik publishes 2 quantizations across 2 models in our index, averaging 4.666 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
2
Quantizations
2
Models covered
2
Avg effective bpw
4.666
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantmajentikvsTheirsDifference
gemma-4-26B-A4BIQ4_XS13.10 GiBbullerwins13.10 GiB-0.0%
gemma-4-26B-A4BIQ4_XS13.10 GiBmradermacher13.10 GiB-0.0%
gemma-4-E4BIQ4_XS4.74 GiBmradermacher4.74 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

ModelQuantizationsSmallest
gemma-4-E4B14.74 GiB
gemma-4-26B-A4B113.10 GiB