Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

NVFP4 post-training quantization

Post-training quantization to NVFP4, including mixed-precision recipes across weights, caches, and an MTP drafter.

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