# Google Research — Accelerating Gemini Nano models on Pixel with frozen Multi-Token Prediction

- Company: Google Research (research.google)
- Announced: 2026-06-26T18:30:00+00:00
- Category: capability-change
- Subject: Research
- Models affected: Gemini Nano v3, Gemma 4
- Source: https://research.google/blog/accelerating-gemini-nano-models-on-pixel-with-frozen-multi-token-prediction/
- Record: https://forck.live/items/1328-accelerating-gemini-nano-models-on-pixel-with-frozen-multi-token-prediction

Google Research introduces a method to retrofit Multi-Token Prediction onto frozen Gemini Nano v3 models, accelerating on-device inference on Pixel 9 and 10 series without separate drafters.

## Evidence

Verbatim from https://research.google/blog/accelerating-gemini-nano-models-on-pixel-with-frozen-multi-token-prediction/:

> We introduce a method to retrofit Multi-Token Prediction onto frozen production models, accelerating on-device inference without the inefficiencies of separate drafters.

---

Record: https://forck.live/items/1328-accelerating-gemini-nano-models-on-pixel-with-frozen-multi-token-prediction
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md