Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Layer-wise mixed INT4/INT8 quantization

A layer-wise scheme assigning INT4 to earlier layers and INT8 to later layers.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See inference quantization for the methods filed beside it.

Also called mixed-precision quantization strategy.

Filed under inference & serving › inference quantization