Techniquesoptimizationquantization-aware training

specific method · filed under optimization

Q4_0 Quantization Format

The Q4_0 quantization format for which the evidence reports QAT checkpoints.

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.

This release includes QAT checkpoints for the popular Q4_0 quantization format

usedoptimizationin Gemma 4 QAT checkpointsGoogle

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency·Google·2026-06-05

Filed alongside

Other methods under optimization :: quantization-aware training.

Quantization-Aware Training FP4 Quantization FP4 Quantization-Aware Training MXFP4 Weights with MXFP8 Activations Stochastic Rounding INT4 Quantization-Aware Training MXFP4 Quantization-Aware Post-Training NVFP4 Training Per-Block Scalar Scaling Quantize-Dequantize Training Random Hadamard Transforms Stochastic Rounding for Mamba Cache Stochastic Rounding of Gradients Straight-Through Estimator