Quantization publisher

samuelchristlie

samuelchristlie publishes 13 quantizations across 1 models in our index, averaging 6.448 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
13
Models covered
1
Avg effective bpw
6.448
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantsamuelchristlievsTheirsDifference
Wan2.1-T2V-1.3BQ5_K_S0.94 GiBcalcuis1.46 GiB-35.5%
Wan2.1-T2V-1.3BQ4_K_S0.83 GiBcalcuis1.29 GiB-35.6%
Wan2.1-T2V-1.3BQ3_K_S0.61 GiBcalcuis0.95 GiB-36.1%

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
Wan2.1-T2V-1.3B130.61 GiB