Google shows how to run Gemma on Raspberry Pi with LiteRT
Google's walkthrough runs Gemma 4 E2B on a Raspberry Pi 5 via LiteRT-LM, hitting 99 tokens/sec prefill and 9 tokens/sec decode, fully offline. The demo powers the Reachy Mini robot to perceive and react to its environment locally in real time.
1 source
Google DeepMind by email
Get an email when Google DeepMind has news
No news that day, no email.
More stories today
- Brad Lightcap, OpenAI's longtime COO, is leaving to 'start something new'
- General Catalyst leads $1.1B round into 2-month-old River AI
- Grok Bot praised for local/cloud agent fleet integration
- BlackRock CEO Larry Fink calls for $500 billion in AI infrastructure funding
- PlusAI reports progress toward 2027 autonomous truck deployments