Does SmolVLA run on ROBOTIS OMX?
Capabilities
| Capability | State | Notes | Evidence |
|---|---|---|---|
| Train / fine-tune | works | ev-hub-adarshkorde-smolvla-omx, ev-hub-imsubin-smolvla-omx, ev-hub-imstevenpmwork-smolvla-omx | |
| Real-robot inference | works with caveats | Remote inference and local guided RTC on hardware per LeRobot main docs and PR #4937; no success metrics. | ev-lerobot-main-remote-readme, ev-lerobot-main-remote-guide, ev-lerobot-pr-4937 |
| Simulation inference | no verified evidence | — | |
| Teleop + record | no verified evidence | — |
Caveats
- Physical-run evidence is post-0.6.1, unreleased LeRobot main (remote-inference docs, PR #4937); no released LeRobot version documents it.
- The upstream support table names the checkpoint (imstevenpmwork/super_chatton_smolvla), not the robot; OMX comes from that checkpoint's training dataset (robot_type=omx_follower) and from the PR's 'Local OMX/SmolVLA' hardware note.
- No task success rate, trial count or latency is published for this run.
Evidence 6 sources; the cell shows the highest tier
- T3 · community reportedhub-checkpointsource 2026-06-16verified 2026-10-25 (today)lerobot 0.5.2
config.json type=smolvla (fine-tuned from lerobot/smolvla_base, 20000 steps); train_config.json dataset imstevenpmwork/super_chatton whose meta/info.json robot_type=omx_follower (100 episodes, front + wrist cameras). Auto-generated card; its rollout command is a placeholder template.
https://huggingface.co/imstevenpmwork/super_chatton_smolvla/blob/1dfe94c5c61f330cb513c6f752095c2de3009ebb/README.md - T1 · upstream documentedofficial-docssource 2026-10-14verified 2026-10-25 (today)lerobot main@d3793b7e36522321c1c455f0dc4826db3793dceb
Post-0.6.1 (unreleased main) remote-inference reference: the policy-support table's 'Execution evidence' column lists imstevenpmwork/super_chatton_smolvla under Remote HW and local guided RTC. It names the checkpoint, not the robot.
“Remote HW and local guided RTC: `imstevenpmwork/super_chatton_smolvla`.”
https://github.com/huggingface/lerobot/blob/d3793b7e36522321c1c455f0dc4826db3793dceb/src/lerobot/remote_inference/README.md - T1 · upstream documentedofficial-docssource 2026-10-14verified 2026-10-25 (today)lerobot main@d3793b7e36522321c1c455f0dc4826db3793dceb
Post-0.6.1 (unreleased main) remote-inference user guide: states SmolVLA checkpoints have run on real robots through the remote-inference path (robots not named).
“ACT, SmolVLA, XVLA, EVO1 and LaWAM checkpoints have run on real robots through this path.”
https://github.com/huggingface/lerobot/blob/d3793b7e36522321c1c455f0dc4826db3793dceb/docs/source/remote_inference.mdx - T3 · community reportedgithub-prsource 2026-10-13verified 2026-10-25 (today)lerobot main@ae2b57f12223c8c5184fcd814eb63cd9ce7de203
Remote-inference PR by imstevenpmwork (LeRobot collaborator; merged into main as ae2b57f, after v0.6.1) reports hardware rollouts with SmolVLA and names OMX for the local SmolVLA guided-RTC checks.
“Local OMX/SmolVLA guided RTC passed recovery and expiry checks.”
https://github.com/huggingface/lerobot/pull/4937 - T3 · community reportedhub-checkpointverified 2026-10-24 (1d ago)
config.json type=smolvla; train_config.json dataset AdarshKorde/omx_pick_green_cube whose meta/info.json robot_type=omx_follower (50 episodes); fine-tuned from lerobot/smolvla_base.
https://huggingface.co/AdarshKorde/omx_smolvla_green_cube_20000 - T3 · community reportedhub-checkpointverified 2026-10-24 (1d ago)
config.json type=smolvla; train_config.json dataset IMsubin/pick_doll_put_pot_omx whose meta/info.json robot_type=omx_follower (100 episodes).
https://huggingface.co/IMsubin/pick_doll_put_pot_omx_smolvla5
SmolVLA inference speed by hardware robot-independent · inference cost only
| Compute | Runtime | Precision | Cams | p50 / p95 ms | Inference | Platform | Source |
|---|---|---|---|---|---|---|---|
| Jetson Orin Nano 8GB (Super) | TensorRT | fp16 | 2 @640x480 | 107.55 / 108.48 | 9.3 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations resized by the exported policy to 512x512; 10 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 1.78 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. | T3 · community reported |
| Jetson Orin Nano 8GB (Super) | ONNX (split) | fp16 | 2 | 189.89 / 190.93 | 5.25 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · tensorrt 10.16.2 (system, via ONNX Runtime TensorRT EP)conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 · onnxruntime-gpu: 1.24 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Configured EP priority 7 graphs TensorRT / 2 CPU. System RAM 2385 MB in use. | T3 · community reported |
| Jetson Orin Nano 8GB (Super) | PyTorch eager | fp32 | 2 | 1167.93 / 1176.65 | 0.86 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · lerobot 0.5.1conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Stock LeRobot SmolVLAPolicy in PyTorch FP32 (LeRobot 0.5.1 env, JetPack-matched torch). RSS peak 3826 MB, system RAM 4126 MB in use. | T3 · community reported |
Embed this cell
Badge for READMEs and model cards. It always shows the current state.
[](https://caniembody.pages.dev/compat/omx/smolvla)<iframe src="https://caniembody.pages.dev/embed/omx/smolvla" width="380" height="132" style="border:0" title="SmolVLA on ROBOTIS OMX | CanIEmbody"></iframe>