Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

4-bit quantization

A general model-quantization setting using 4-bit precision; no particular algorithm or format is specified.

The sources on this page name it without explaining how it works. The line above is the extraction's one-line gloss. See inference quantization for the methods filed beside it.

Also called 4-bit model quantization.

Filed under inference & serving › inference quantization