Model techniques map
Techniquesoptimizationquantization-aware training

general family · filed under optimization

Quantization-Aware Training

Training a model with quantization in the loop so it can adapt to quantized computation; the evidence does not specify a single bit format.

Also called Quantization-Aware Training (QAT).

sources
8
models
4
labs adopt it
3
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 7core 1

Documented in

Evidence

8 spans quoted from the sources, strongest treatment first.

By simulating quantization during training, QAT minimizes quality loss when the model is compressed.

coreoptimizationin Gemma 4 QAT checkpointsGoogle

Kimi K3 applies quantization-aware training from the SFT stage onward, using MXFP4 weights with MXFP8 activations for broad hardware compatibility.

usedpost trainingin Kimi K3Moonshot AI

In addition, we apply quantization-aware training (QAT) from the SFT stage onward, with MXFP4 weights and MXFP8 activations (§ 4.1.4).

usedunclearin Kimi K3Moonshot AI

Quantization-aware training starts at the supervised fine-tuning stage, using MXFP4 weights and MXFP8 activations

usedtraining objectivein Kimi K3Moonshot AI

We provide quantized versions of our models trained with quantization-aware training [Jacob et al., 2018, QAT] to reduce their parameter memory footprint and latency with minimal impact on quality.

usedpost trainingin Gemma 4Google DeepMind

we introduce Quantization-Aware Training (QAT) [QAT] during the post-training stage

usedpost trainingin DeepSeek-V4DeepSeek

K3 employs quantization-aware training (QAT) starting from the supervised fine-tuning stage, not post-training quantization.

usedtraining objectivein Kimi K3Moonshot AI

Kimi K3 applies quantization-aware training from the SFT stage onward, using MXFP4 weights with MXFP8 activations for broad hardware compatibility.

usedtraining objectivein Kimi K3Moonshot AI

Filed alongside

Other methods under optimization :: quantization-aware training.