Quantization publisher

inclusionAI

inclusionAI publishes 5 quantizations across 1 models in our index, averaging 7.795 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 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
7.795
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantinclusionAIvsTheirsDifference
Ling-mini-2.0Q2_K5.65 GiBbartowski5.44 GiB+3.8%
Ling-mini-2.0Q4_K_M9.23 GiBbartowski9.26 GiB-0.3%
Ling-mini-2.0Q6_K12.45 GiBbartowski12.47 GiB-0.1%
Ling-mini-2.0Q8_016.12 GiBbartowski16.12 GiB-0.0%
Ling-mini-2.0BF1630.30 GiBbartowski30.30 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
Ling-mini-2.055.65 GiB