Model techniques map
Techniquesinference & servinginference quantization

specific method · filed under inference & serving

Mobile quantization

Uses per-channel low-bit weights and INT8 activations for mobile hardware; the cited weights mix INT2 and INT4.

source
1
model
1
lab adopt it
1
strongest
optional

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

mobile quantization: per-channel low bitwidth weight (mix of int2 and int4) and activation quantization (int8).

optionalinference servingin Gemma 4Google DeepMind

Filed alongside

Other methods under inference & serving :: inference quantization.