Google Found a Way to Make Local AI Up to 3x Faster—No New Hardware Required

In brief

• Google released Multi-Token Prediction (MTP) drafters for Gemma 4, delivering up to a 3x speedup at inference without any degradation in output quality.
• The technique—called speculative decoding—uses a lightweight "drafter" model to predict several tokens at once, which the main model then verifies in parallel, bypassing the one-token-at-a-time bottleneck.
• MTP drafters are available on…