Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

ModelOpt FP4 quantization

FP4 quantization invoked through the ModelOpt quantization configuration; no further method details are given.

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.

Filed under inference & serving › inference quantization