Does GR00T N1.7 run on ROBOTIS OMX?

works with caveats

T3 · community reportedlast verified 2026-10-24 · 1d agoIsaac GR00T

Capabilities

Capability	State	Notes	Evidence
Train / fine-tune	works		ev-hub-pseudolab-groot-omx-2cam, ev-hub-pseudolab-groot-omx
Real-robot inference	works with caveats	Only qualitative real-robot feedback is given (no success rates); reported metrics are open-loop MSE.	ev-hub-pseudolab-groot-omx-2cam
Simulation inference	no verified evidence		—
Teleop + record	no verified evidence		—

Caveats

Community-reported only; not documented upstream or maintainer-tested.
Trained and served with NVIDIA's Isaac-GR00T stack (NEW_EMBODIMENT tag, GR00T policy server), not LeRobot's groot policy; the dataset uses ROBOTIS's robot_type string omx_f rather than LeRobot's omx_follower.
The authors report that the single top-down-camera model closed the gripper before reaching the object during real-robot deployment (height perception); their 2-camera successor adds a wrist camera to address it.

Evidence 2 sources; the cell shows the highest tier

T3 · community reportedhub-checkpointverified 2026-10-24 (1d ago)
Model card: fine-tune of nvidia/GR00T-N1.7-3B (NEW_EMBODIMENT, frozen backbone) for the 'ROBOTIS Open Manipulator-X' (card wording) 'Pick up dolls' task on pseudolab/omx_f_PickUpDollWith2Cam, whose meta/info.json robot_type=omx_f (94 episodes); state is 5 arm joints + gripper. The card cites real-robot deployment of the 1-camera predecessor.
https://huggingface.co/pseudolab/GR00T-N1.7-3B-OMX-PickupDolls-2Cam
T3 · community reportedhub-checkpointverified 2026-10-24 (1d ago)
Model card: GR00T N1.7-3B fine-tuned (NEW_EMBODIMENT) for the Open Manipulator-X 5-DoF + gripper doll pick-up task on 75 teleoperated episodes plus Cosmos-Transfer2.5 augmentation; open-loop MSE only.
https://huggingface.co/pseudolab/GR00T-N1.7-3B-OMX-PickupDolls

GR00T N1.7 inference speed by hardware robot-independent · inference cost only

Compute	Runtime	Precision	Cams	p50 / p95 ms	Inference	Platform	Source
H100 80GB	TensorRT	bf16	2 @256x256	22.9 / —	43.67 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
RTX PRO 6000 Blackwell Server	TensorRT	bf16	2 @256x256	24.7 / —	40.49 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
L40	TensorRT	bf16	2 @256x256	35 / —	28.57 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
Jetson AGX Thor 128GB	TensorRT	mixed	2 @256x256	35.6 / —	28.09 Hz	jetpack 7.2 · power_mode MAXN with jetson_clocks · cuda 13.2 · torch 2.13.0 conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Mixed NVFP4 quantization (enum has no fp4 value).	T3 · community reported
RTX PRO 6000 Blackwell Server	torch.compile	bf16	2 @256x256	52.1 / —	19.19 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
H100 80GB	torch.compile	bf16	2 @256x256	53.4 / —	18.73 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
L40	torch.compile	bf16	2 @256x256	66.8 / —	14.97 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
RTX PRO 6000 Blackwell Server	PyTorch eager	bf16	2 @256x256	75.7 / —	13.21 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
Jetson AGX Thor 128GB	TensorRT	bf16	2 @256x256	76.8 / —	13.02 Hz	jetpack 7.2 · power_mode MAXN with jetson_clocks · cuda 13.2 · torch 2.13.0 conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
Jetson AGX Thor 128GB	torch.compile	bf16	2 @256x256	100.5 / —	9.95 Hz	jetpack 7.2 · power_mode MAXN with jetson_clocks · cuda 13.2 · torch 2.13.0 conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
H100 80GB	PyTorch eager	bf16	2 @256x256	101.5 / —	9.85 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
Jetson AGX Thor 128GB	PyTorch eager	bf16	2 @256x256	106.8 / —	9.36 Hz	jetpack 7.2 · power_mode MAXN with jetson_clocks · cuda 13.2 · torch 2.13.0 conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
L40	PyTorch eager	bf16	2 @256x256	123.7 / —	8.08 Hz	— conditions torch_threads: 8 intra-op / 1 inter-op Inference cost only; not task success. Median of 60 timed calls (3 repetitions x 20 after 10 warmup), fixed inputs, includes preprocessing and action decoding, excludes RPC. Precision is the repo default (unquantized BF16).	T3 · community reported
Jetson Orin Nano 8GB (Super)	TensorRT	fp16	3 @640x480	273.7 / 275.4	3.66 Hz	jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10 conditions board: 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 256x256; 4 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 5.78 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. Three camera views, each with two frames (GR00T N1.7 temporal input).	T3 · community reported

Embed this cell

Badge for READMEs and model cards. It always shows the current state.

[![GR00T N1.7 on ROBOTIS OMX: works with caveats](https://caniembody.pages.dev/badge/omx/groot-n1-7.svg)](https://caniembody.pages.dev/compat/omx/groot-n1-7)

<iframe src="https://caniembody.pages.dev/embed/omx/groot-n1-7" width="380" height="132" style="border:0" title="GR00T N1.7 on ROBOTIS OMX | CanIEmbody"></iframe>

History

2026-10-25 fecccd1 Initial release: robot policy compatibility matrix · Danilo Znamerovszkij