Quantization publisher

owao

owao publishes 14 quantizations across 1 models in our index, averaging 5.686 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 7 of the pairs we can compare — the same label does not mean the same file.

From the file· summed file bytes
Repositories
1
Quantizations
14
Models covered
1
Avg effective bpw
5.686
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantowaovsTheirsDifference
Nanbeige4.2-3BQ5_K_M2.78 GiBAbiray2.78 GiB-0.0%
Nanbeige4.2-3BQ4_K_M2.40 GiBAbiray2.40 GiB-0.0%
Nanbeige4.2-3BQ4_K_S2.33 GiBAbiray2.33 GiB-0.0%
Nanbeige4.2-3BQ3_K_M2.02 GiBAbiray2.02 GiB-0.0%
Nanbeige4.2-3BQ6_K3.19 GiBAbiray3.19 GiB-0.0%
Nanbeige4.2-3BQ8_04.13 GiBAbiray4.13 GiB-0.0%
Nanbeige4.2-3BQ8_04.13 GiBAndgihat4.13 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
Nanbeige4.2-3B141.64 GiB