Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Platform-dependent W4A4/W4A16 quantization

Inference uses W4A4 on Blackwell and W4A16 on non-Blackwell platforms.

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