Quantization publisher

desirel

desirel publishes 14 quantizations across 1 models in our index, averaging 5.771 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 6 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
5.771
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantdesirelvsTheirsDifference
WAN2.2-14B-Rapid-AllInOneQ8_016.44 GiBbefox17.37 GiB-5.4%
WAN2.2-14B-Rapid-AllInOneQ8_016.44 GiBbefox17.37 GiB-5.4%
WAN2.2-14B-Rapid-AllInOneQ6_K12.80 GiBbefox13.51 GiB-5.3%
WAN2.2-14B-Rapid-AllInOneQ6_K12.80 GiBbefox13.51 GiB-5.3%
WAN2.2-14B-Rapid-AllInOneQ2_K5.59 GiBbefox6.24 GiB-10.3%
WAN2.2-14B-Rapid-AllInOneQ2_K5.59 GiBbefox6.24 GiB-10.3%

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
WAN2.2-14B-Rapid-AllInOne145.59 GiB