Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Low-bit quantization

A general family of quantization methods using low-bit representations, without a specific format or algorithm identified.

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 low-bit methods.

Filed under inference & serving › inference quantization