Quantization publisher

smarttasks

smarttasks publishes 4 quantizations across 1 models in our index, averaging 6.484 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
4
Models covered
1
Avg effective bpw
6.484
across their files

Same model, same quant label, different bytes

largest disagreements first
ModelQuantsmarttasksvsTheirsDifference
VibeThinker-1.5BQ5_K_M1.20 GiBmradermacher1.20 GiB-0.0%
VibeThinker-1.5BQ4_K_M1.04 GiBmradermacher1.04 GiB-0.0%
VibeThinker-1.5BQ6_K1.36 GiBmradermacher1.36 GiB-0.0%
VibeThinker-1.5BQ8_01.76 GiBmradermacher1.76 GiB-0.0%
VibeThinker-1.5BQ6_K1.36 GiBMaziyarPanahi1.36 GiB-0.0%
VibeThinker-1.5BQ5_K_M1.20 GiBMaziyarPanahi1.20 GiB-0.0%
VibeThinker-1.5BQ4_K_M1.04 GiBMaziyarPanahi1.04 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
VibeThinker-1.5B41.04 GiB