Quantization publisher

mahdisml

mahdisml publishes 1 quantizations across 1 models in our index, averaging 4.967 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
1
Models covered
1
Avg effective bpw
4.967
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantmahdismlvsTheirsDifference
Huihui-Qwen3-4B-Instruct-2507-abliteratedQ4_K_M2.33 GiBmradermacher2.33 GiB-0.0%
Huihui-Qwen3-4B-Instruct-2507-abliteratedQ4_K_M2.33 GiBprithivMLmods2.33 GiB-0.0%
Huihui-Qwen3-4B-Instruct-2507-abliteratedQ4_K_M2.33 GiBprithivMLmods2.33 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
Huihui-Qwen3-4B-Instruct-2507-abliterated12.33 GiB