# Quantization-aware training

> Quantization-aware training: Simulating low precision during training so the model learns to work well in it. It does not make training faster.

Canonical: https://llmdojo.dev/glossary/qat

Also called qat.

Simulating low precision during training so the model learns to work well in it. It does not make training faster.

Learn it in the lesson: [What to quantize, and when](https://llmdojo.dev/learn/inference-optimization/precision-and-quantization/what-and-when) (Inference and Model Optimization · Precision and Quantization: Fewer Bytes per Weight).

## Interview questions about Quantization-aware training

- [Explain quantization-aware training, knowledge distillation, eval mode and contrastive learning. How would you verify that each one improved a production model?](https://llmdojo.dev/interview/q/explain-quantization-aware-training-knowledge-distillation-eval-mode-and-contrastive-learning-how)

## Related
- [Quantization](https://llmdojo.dev/glossary/quantization)
- [BF16 (bfloat16)](https://llmdojo.dev/glossary/bf16)
- [Post-training quantization](https://llmdojo.dev/glossary/ptq)
- [Glossary of every term](https://llmdojo.dev/glossary)