Gemini Robotics On-Device 2

An on-robot version of the vision-language-action model that runs locally rather than in the cloud: text instructions, camera images and numeric sensor readings in, robot actions as numbers out. Built on the Gemini Robotics 1.5 architecture with on-device Gemma models.

Дата карточки модели — 30.07.2026. Доступ только избранным доверенным тестировщикам по заявке.

Understands

text, images

Produces

text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.