Gemini Robotics On-Device 2 is the on-device vision-language-action member of Google DeepMind’s Robotics 2 release, with access and control responsibilities distinct from the other family members.
The on-device variant targets local execution. The announcement shows adaptation to named partner embodiments; those demonstrations do not establish compatibility with arbitrary cameras, grippers or controllers.
Google DeepMind · Published 2026-07-30 · Source accessed 2026-09-28
Embodiment
Not publicly disclosed
Implementation & training
Compute
Not publicly disclosed
Training-data disclosures
Not publicly disclosed
Integrations
Not publicly disclosed
Reported benchmark results
Context before scores. Results from different benchmarks are not directly comparable. A simulation result does not establish real-world reliability, safety or commercial availability.
No result meets our complete revision and methodology requirements for this record yet. Inspect the original benchmark documentation before comparing published scores.
What this evidence does not establish
Public demonstrations are embodiment-specific; public weight terms were not verified.
Pricing and public checkpoint revision were not verified.
Related reading is an editorial crosslink. Sourced connections describe relationships reported in the cited material. A link to a versioned profile does not establish compatibility with that version unless the connection note explicitly identifies it.