Accelerating Gemma 4: faster inference with multi-token prediction draftersknowledge-baseMay 11, 2026By Team M37Labshttps://blog.google/innovation-and-ai/technology/developers-tools/multi-token-prediction-gemma-4/GoogleAccelerating Gemma 4: faster inference with multi-token prediction draftersAn overview of how Multi-Token Prediction (MTP) drafters are making Gemma 4 models up to 3x faster at inference.blog.google