Model techniques map
Techniquesoptimizationquantization-aware training

specific method · filed under optimization

FP4 Quantization-Aware Training

Quantization-aware training using FP4, specifically MXFP4 in the evidence, to adapt model components to low-precision computation.

Also called MXFP4 quantization-aware training, MXFP4 quantization-aware training (QAT).

sources
3
models
4
labs adopt it
2
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 3

Documented in

Evidence

3 spans quoted from the sources, strongest treatment first.

We employ MXFP4 quantization-aware training (QAT) during mid-training, allowing the model to adapt to low-precision computation while preserving model quality.

usedoptimizationin MiMo-V2.6Xiaomi

we incorporate FP4 quantization-aware training for MoE expert weights and the indexer QK path

usedpost trainingin DeepSeek-V4DeepSeek

FP4 Quantization-Aware Training applies MXFP4 quantization to MoE expert weights and the indexer QK path during post-training.

usedpost trainingin DeepSeek-V4DeepSeek

Filed alongside

Other methods under optimization :: quantization-aware training.