Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

NVFP4 weight quantization with BF16 activations

LiLiCorr linear-layer weights use NVFP4 while activations remain BF16.

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