# Gemma 4 E4B and EmbeddingGemma 2 run a Reachy Mini robot car offline

> Original title: How does it work under the hood?

- Source: Google Gemma
- Published: 2026-10-30T16:37:19.000Z
- Bad Influence: https://badinfluence.news/items/ec6fkyeklmofb4qg6bzbg6sbs
- Original: https://x.com/googlegemma/status/2116207834191044772

## Summary

Google's Gemma team says a Reachy Mini robot car runs two Gemma models on the LiteRT runtime. Gemma 4 E4B runs locally to handle voice conversation and issue tool calls that start and stop the car. EmbeddingGemma 2 runs on an Arduino VentunoQ board to steer the robot from real-time camera input, and the team says the whole loop stays private, offline, and low-latency.

## Post

How does it work under the hood?

It uses two Gemma models running on Google’s LiteRT runtime:

1️⃣ Conversation & Tool Calling:
When you speak to Reachy Mini by voice. Gemma 4 E4B runs locally to hold natural conversations and issues a tool call to start or stop the car.

2️⃣ Real-Time Vision & Driving:
Once in motion, a small Gemma-based decision model (EmbeddingGemma 2) runs directly on an @arduino  VentunoQ embedded board to steer the robot using real-time camera input.

Because both models run on LiteRT, the whole loop stays completely private, offline, and with low-latency.

Check out @IanBallantyne’s breakdown for more technical details on the build!

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2116205678511697921%2Fimg%2F84QVHsFlqQUZEQri.jpg&mode=thumb&exp=1793577600&sig=7d600550dd690336)