Quantization publisher

artokun

artokun publishes 5 quantizations across 1 models in our index, averaging 3.595 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
1
Quantizations
5
Models covered
1
Avg effective bpw
3.595
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantartokunvsTheirsDifference
gemma-4-12B-it-hereticQ5_K_M5.37 GiBJMingo7.84 GiB-31.5%
gemma-4-12B-it-hereticQ4_K_M4.97 GiBJMingo6.63 GiB-25.1%
gemma-4-12B-it-hereticQ4_K_M6.87 GiBJMingo6.63 GiB+3.6%

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-4-12B-it-heretic53.19 GiB