NVIDIA fits Gemma 4 E4B robot brain on an 8GB Jetson with vision, chat and tool calls
huggingface · x · 2026-11-11
Google's Gemma team highlighted an NVIDIA AI demo putting a Gemma 4 E4B-based model into a robot body, all running on a single 8GB Jetson — handling live conversation, tool calls, animations, and a vision model at once.
The robot's first act: scanning the room, spotting the giant TV, and starting a movie break, showcasing on-device multimodal autonomy for small models.
More from Embodied
- Niantic Spatial adds object interaction in Gaussian Splats for embodied AI real2sim training — Scobleizer · 2026-11-11
- SpaceX unveils Starlink Mini 2 with built-in 71Wh battery, up to 4.5 hours runtime — Scobleizer · 2026-11-11
- VLK generates large-scale synthetic data for humanoid loco-manipulation without teleoperation — pabbeel · 2026-11-11
- MacroData Labs launches MacroHands, SOTA 3D hand models from egocentric video — gui_penedo · 2026-11-11
- Otto One launches a home box where AI agents live locally with cloud-model fallback routing — rohanpaul_ai · 2026-11-11
- Newton physics engine ships FBA solver, enabling cloth sim2real in minutes — ChongZzZhang · 2026-11-11