Model techniques map
Techniquesinference & servinginference quantization

implementation detail · filed under inference & serving

W4A16 quantization

Uses 4-bit weights and 16-bit activations, with the cited example specifying NVFP4 weights and BF16 activations.

Also called W4A16 (weights NVFP4, activations BF16), W4A16.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

W4A16 (weights NVFP4, activations BF16)

usedinference servingin Nemotron 3 UltraNVIDIA

Filed alongside

Other methods under inference & serving :: inference quantization.