As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/gr00t-n1-7/

# Isaac GR00T N1.7

NVIDIA, Isaac GR00T family. Status: current. Type: robotics model. Released: 2026-04-17.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `nvidia/GR00T-N1.7-3B` |  | https://huggingface.co/blog/nvidia/gr00t-n1-7 https://huggingface.co/nvidia/GR00T-N1.7-3B |
| GitHub |  |  | https://github.com/NVIDIA/Isaac-GR00T |
| Hugging Face LeRobot integration |  |  | https://blogs.nvidia.com/blog/hugging-face-lerobot-models-frameworks-open-robotics/ |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, image
- Output: action
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: NVIDIA Open Model License (weights, commercial use); Apache-2.0 (code)

## Where it stands

- Newer robotics models in the registry since its release: 12. The 5 newest:
  - Praxis-1 (2026-09-30) https://postcutoff.com/m/praxis-1/
  - Helix 2.5 (2026-09-17) https://postcutoff.com/m/figure-helix-2-5/
  - UnifoLM-WLA-1.0 (2026-09-10) https://postcutoff.com/m/unifolm-wla-1-0/
  - Skild S1 (Skild Brain) (2026-08-25) https://postcutoff.com/m/skild-s1/
  - Generalist GEN-1.5 (2026-08-19) https://postcutoff.com/m/generalist-gen-1-5/
- Before it from NVIDIA: Isaac GR00T N2 (2026-03-16) https://postcutoff.com/m/gr00t-n2/
- Weights are public. Licence: NVIDIA Open Model License; Apache-2.0. See the licence for commercial terms.

## What stands out

- Human egocentric video pretraining: Pretrained on 20,854 hours of human egocentric video (EgoScale) across 20+ task categories, on top of robot data. Source: https://huggingface.co/blog/nvidia/gr00t-n1-7
- Scaling law for robot dexterity (first): NVIDIA reports the 'first-ever scaling law for robot dexterity': more human video predictably improves 22-DoF hand performance without mass teleoperation. Source: https://huggingface.co/blog/nvidia/gr00t-n1-7
- Reasoning VLA on a Cosmos backbone: 3B 'Action Cascade' model: Cosmos-Reason2-2B VLM plus 32-layer diffusion transformer; relative end-effector action space; runs on one 16 GB+ GPU including Jetson Thor/Orin and DGX Spark. Source: https://github.com/NVIDIA/Isaac-GR00T

## Notes

Early access with commercial licensing announced at GTC 2026-03-16; open release/HF blog 2026-04-17. Post-trained checkpoints: GR00T-N1.7-LIBERO, -DROID, -SimplerEnv-Bridge, -SimplerEnv-Fractal, GR00T-H-N1.7 (surgical-robotics variant, uploaded to HF 2026-05-30: 3B, post-trained on 601 h / ~63.9k episodes of real surgical tasks from the Open-H-Embodiment dataset across 7 platforms incl. dVRK, CMR Versius, KUKA LBR iiwa; NVIDIA Open Model License; R&D only, not for clinical use; follows the original GR00T-H announced at GTC 2026-03-16). Backbone nvidia/Cosmos-Reason2-2B is gated (accept license on HF). Validated on Unitree G1, YAM bimanual, AGIBot Genie 1. Fine-tuning: 40 GB+ GPUs recommended.

The current open GR00T release; GR00T N2 (world action model) is due by end of 2026.

Changelog: 2026-09-29 added GR00T-H-N1.7 details.

Sources: [GR00T-H-N1.7 model card](https://huggingface.co/nvidia/GR00T-H-N1.7), [HF blog](https://huggingface.co/blog/nvidia/gr00t-n1-7), [GitHub](https://github.com/NVIDIA/Isaac-GR00T), [NVIDIA newsroom (GTC 2026)](https://nvidianews.nvidia.com/news/nvidia-and-global-robotics-leaders-take-physical-ai-to-the-real-world).

Model page: https://postcutoff.com/m/gr00t-n1-7/