MotionBricks Desktop
Generate a short Unitree G1 motion transition from four recent poses and four target poses with the official MotionBricks ONNX graph. Returns complete pose, foot-contact and token tensors.
Desktop app
Run MotionBricks Desktop on your computer
Download the desktop app to load this model, provide input and view results locally.
Public desktop downloads are coming soon.Device requirements
If your device falls short
MemoryAdvisory only: close other apps, reduce image/tile/token/batch settings or choose a smaller verified model/precision. CPU can need more RAM than GPU.
GPUIf the selected GPU runtime fails, existing CPU fallback may recover when enabled, but CPU has its own memory/runtime needs.
PlatformUse a compatible OS/architecture/runtime or another model. These estimates do not add hardware detection or block runs.
Benchmark evidence
Saved desktop measurements apply to the recorded hardware and runtime. Fallback cases report the device that actually ran; they do not prove GPU support on the requested device.
MotionBricks Unitree G1 Desktop
2 configurations testedQuality criteria
{ "scope": "G1 internal NVIDIA-technology evaluation on provider walk recording; not redistributable sample media. Hand-authored independent pose fixtures required separately for published app samples.", "minimumTokenCount": 6, "maximumTokenCount": 16, "maximumInferenceMs": 10000, "maximumEndpointRootErrorM": 0.15, "maximumAdjacentRootStepM": 0.15, "maximumMeanEndpointJointErrorRad": 0.35, "maximumAdjacentJointStepRad": 0.8, "fixtureSource": "NVlabs/motionbricks@54fc563aeaaf819a753d72cc9fdc6713989cdd43/assets/motions/unitree_g1/locomotion/bs_1d_linear/Neutral_walk_forward_002__A057.csv", "fixtureLicense": "NVIDIA Sample Data Evaluation License; retain locally for internal evaluation only; never publish or mirror recording or derivatives." }
| Precision | Device | Result | Platform | Inference / load | |
|---|---|---|---|---|---|
FP32 | cpu | Passed | Very fast | Not recorded | 25 ms / 947 ms |
FP32 | cpu | Passed | Very fast | Not recorded | 42 ms / 947 ms |
Test setup & sample details
- Quality gate
- { "scope": "G1 internal NVIDIA-technology evaluation on provider walk recording; not redistributable sample media. Hand-authored independent pose fixtures required separately for published app samples.", "minimumTokenCount": 6, "maximumTokenCount": 16, "maximumInferenceMs": 10000, "maximumEndpointRootErrorM": 0.15, "maximumAdjacentRootStepM": 0.15, "maximumMeanEndpointJointErrorRad": 0.35, "maximumAdjacentJointStepRad": 0.8, "fixtureSource": "NVlabs/motionbricks@54fc563aeaaf819a753d72cc9fdc6713989cdd43/assets/motions/unitree_g1/locomotion/bs_1d_linear/Neutral_walk_forward_002__A057.csv", "fixtureLicense": "NVIDIA Sample Data Evaluation License; retain locally for internal evaluation only; never publish or mirror recording or derivatives." }
- Tested
- 2026-11-16T15:18:09Z
- Environment
- Apple M3 Max96GiB/macOS27.2; exact original staged graph; app-owned pinned CPython3.13.18/ORT1.23.2/NumPy2.3.4; four CPU threads; existing background mirror active.
- Runtime
- onnxruntime 1.23.2
- Artifact revision
- 54fc563aeaaf819a753d72cc9fdc6713989cdd43
- Fixture
{ "file": "model-samples/motionbricks-g1/standing-input.json", "size": 5678, "sha1": "402501f9b8d98a911549dab33c78722f7d1ac1ef", "sha256": "a9cd8eff52d8e7a7fe64be2c093760f999e99e78b6838649d8843cc2675879c1", "url": "https://assets.localai.tools/samples/v1/files/a9cd8eff52d8e7a7fe64be2c093760f999e99e78b6838649d8843cc2675879c1/standing-input.json" }- Rerun when
- artifact revision; runtime version; fixture checksum; quality gate; backend behavior
Per-case quality & failure details
[
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"scope": "Authored pose contract case; independent real-walk task-quality evidence retained separately.",
"finite": true,
"tokenCount": 11,
"passed": true,
"endpointRootErrorM": 0.0024166453210013343,
"meanEndpointJointErrorRad": 0.018484704434100926,
"maxRootStepM": 0.00020890705755897916,
"maxJointStepRad": 0.03432340919971466
},
"runtime": {
"inferenceMs": 42.11441599909449,
"durationMs": 65.21929099835688,
"framesPerSecond": 902.3038572069252,
"placement": {
"CPUExecutionProvider": 3754
},
"gpuPlanOperations": 0,
"provider": "CPUExecutionProvider",
"acceleration": "cpu",
"visualizationMs": 0.25091699353652075,
"loadMs": 947.0954579956015,
"totalMs": 989.209873994696,
"grade": "good",
"actualDevice": "cpu",
"actualPrecision": "fp32",
"engine": "onnxruntime",
"version": "1.23.2",
"artifactRevision": "54fc563aeaaf819a753d72cc9fdc6713989cdd43",
"precision": "fp32",
"device": "cpu"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"scope": "Authored pose contract case; independent real-walk task-quality evidence retained separately.",
"finite": true,
"tokenCount": 11,
"passed": true,
"endpointRootErrorM": 0.026404230351798917,
"meanEndpointJointErrorRad": 0.02190343778066594,
"maxRootStepM": 0.015825942082508128,
"maxJointStepRad": 0.04737675189971924
},
"runtime": {
"inferenceMs": 25.402582999959122,
"durationMs": 25.66004200343741,
"framesPerSecond": 1495.9108685939989,
"placement": {
"CPUExecutionProvider": 3754
},
"gpuPlanOperations": 0,
"provider": "CPUExecutionProvider",
"acceleration": "cpu",
"visualizationMs": 0.19137500203214586,
"loadMs": 947.0954579956015,
"totalMs": 972.4980409955606,
"grade": "good",
"actualDevice": "cpu",
"actualPrecision": "fp32",
"engine": "onnxruntime",
"version": "1.23.2",
"artifactRevision": "54fc563aeaaf819a753d72cc9fdc6713989cdd43",
"precision": "fp32",
"device": "cpu"
}
}
]Release validation still required
- Complete verified execution-dependency backup and cold model/runtime/package source recovery acceptance.