A model is still running

A model is still running or downloading. Leaving will stop the current operation. Stay on this page to let it finish.

Skip to content
LocalAI.toolsBeta

Join the waitlist

Get an email when the new apps and model runs launch.

No account needed.

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 inferencePrivate · Runs on your computer
About this model

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.

Created by
NVIDIA
Model released
Unknown
Source repository created
Oct 23, 2026
Model weights · FP32
734.3 MB

Best for

  • Offline animation and pose-transition exploration on the exact G1 skeleton.
  • Inspect raw model-space motion and predicted contact timelines.

Keep in mind

  • G1 joint coordinates only, in Z-up,+X-forward model space, meters,radians and unit XYZW root quaternions; no text, video, scene geometry or arbitrary skeleton input.
  • Raw output contains boundary and unused frames. Only the leading4×pred_num_tokens frames are meaningful; trim three frames at each end for playback. Raw foot-contact regression can exceed0–1; the visualization clamps display values, leaving raw tensors unchanged.
  • No endpoint correction, root smoothing, world alignment, tracking controller or physics simulation is applied. Not a physical robot controller or safety/limit validation.
  • Quality scope: internal provider walking recording plus two authored pose cases; not broad motion-quality certification.
  • Measured native CPU on Apple M3 Max. CoreML static-batch GPU placement and numerical parity pass but cold compilation246s and first inference2.64s are much slower than CPU; GPU app/packaged qualification is deferred. Atomic graph has no incremental streaming.
  • Complete verified execution-dependency backup and cold model/package source recovery remain pending. Normal production browser and native CPU app/history/replay scopes are qualified; broader backends/platforms are separate.

Processed on your deviceYour input is processed locally in the desktop app. Model and runtime files download from external hosts.

Target platforms · verification required

  • macos · aarch64, x86_64
  • windows · x86_64

Recommended configuration

FP32 · cpu (verified platform only)

Sources & technical details
Original model
https://huggingface.co/nvidia/MotionBricks
Release verification
Unknown
Release evidence
Exact original public checkpoint release day not established; repository creation, paper date and ONNX update are distinct.
Source updated
Oct 23, 2026
Native model files
NVlabs/motionbricks
Files updated
Oct 26, 2026
Artifact revision
54fc563aeaaf819a753d72cc9fdc6713989cdd43

Desktop app

Sample result

MotionBricks Unitree G1 Desktop

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

macOS Apple SiliconCPU / FP32Tested8.0 GiBRAM estimate
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 tested
Passed2
Failed0
TestedNov 16, 2026
Runtimeonnxruntime 1.23.2

Quality 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." }

PrecisionDeviceResultPlatformInference / load
FP32cpuPassedVery fastNot recorded25 ms / 947 ms
FP32cpuPassedVery fastNot recorded42 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.

Something not quite right?

Tell us what happened with MotionBricks Desktop. Loading, results, or the page itself—we’re here for all of it.

Attachments Optional

Up to 3 files · 50 MB each

Browser, OS, CPU/GPU, memory, screen, storage, and network details are included automatically. Model inputs, results, and browsing history are not collected.