Quantization publisher

sudomoniker

sudomoniker publishes 1 quantizations across 1 models in our index, averaging 8.905 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 2 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
8.905
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantsudomonikervsTheirsDifference
all-MiniLM-L6-v2Q8_00.02 GiBleliuga0.02 GiB+1.1%
all-MiniLM-L6-v2Q8_00.02 GiBsecond-state0.02 GiB+1.1%

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
all-MiniLM-L6-v210.02 GiB