Google shows Gemma 4 E2B running on Raspberry Pi 5 with LiteRT

Google's walkthrough runs Gemma 4 E2B on a Raspberry Pi 5 via LiteRT-LM at 99 tokens/sec prefill and 9 tokens/sec decode, fully on-device. The guide demoes a Reachy Mini robot perceiving and reacting to its environment locally in real time.
2 sources
Google DeepMind by email
Get an email when Google DeepMind has news
No news that day, no email.
More stories today
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills
- Aident Loadout gives agents 27,000+ tools and logs every action
- Etched gains sizable fan base for AI inferencing computers
- Corbell generates technical specs from repository knowledge graphs