Released 2026-02-11 · robotics vla
Deployment evidence
Xiaomi Robotics · 4.7B total · 4.7B active · Not applicable
Best-fit scenarios
Real-time robotic manipulation research and post-training across supported embodiments and simulation suites.
Not recommended
- Direct deployment on an unvalidated physical robot
- Safety-critical control without independent interlocks and task-specific validation
Robot manipulation
Vendor-statedThe official deployment guide targets robotic manipulation with asynchronous real-time execution.
Capability sourceLIBERO, CALVIN and SimplerEnv evaluation
Public evidenceOfficial fine-tuned checkpoints and evaluation guides are released for all three suites.
Capability sourceEmbodiment-specific post-training
Vendor-statedPost-training code is available for adapting the model to new data.
Capability sourceOfficial launch / minimum
Evidence CConsumer gpu claim no vram
The vendor says BF16 inference is optimized for consumer GPUs but publishes no exact minimum VRAM. Primary recipe
200-person team
Evidence ERobot fleet profile required
Size by robots, camera rate and control latency; a 200-seat office profile is not applicable.
Commercial API
Evidence EEdge control not public api
Prefer an on-robot or near-edge safety architecture; a remote multi-tenant API is not the default production shape.
Commercial-use check
Apache-2.0
MaaS / hosted service: No model-specific MaaS restriction identified in Apache-2.0.
Attribution: Provide the license and notices, preserve attribution notices, and mark modified files.
Known limitations and open questions
- Simulation benchmarks do not prove physical-world safety
- Exact VRAM and end-to-end control latency are not published