available
Weights
Pre-trained N1.7 weights are linked from the official repository.
Inspect this claim’s source ↗NVIDIA / FAMILY RECORD
Isaac GR00T
An open vision-language-action model for generalized humanoid skills, accompanied by reference code, data tooling, and a robotics development stack.
Checked release: GR00T N1.7
Sources checked 2026-09-19
- GR00T N1.7 early-access release
- · Primary source
The cited official release is labelled early access; this record does not imply a later general-availability date.
The profile describes this checkpoint, not every release carrying the family name. Developer documentation is not independent reproduction.
THE MODEL / THE TERMS
Know what you are picking up.
- Parameters
- Not stated in the reviewed N1.7 overview
- Architecture
- Vision-language-action foundation model combining perception, language instruction, and robot action generation.
- Modalities
- text · image · video · robot state · robot action
- Context
- Not established as a language-token context window in the reviewed release.
- Weights license
- NVIDIA Open Model License / repository-specific terms
- Commercial use
- Review the model and data licenses for the intended robot, dataset, and deployment.
- Memory
- Hardware requirements vary by robot platform and inference stack; no universal minimum is asserted.
- Known quantizations
- Deployment formats are hardware- and runtime-specific
Specifications are developer-reported. Primary release documentation ↗ · All sources and terms
NINE DIMENSIONS / NO OPENNESS SCORE
What is actually available?
Each component has its own evidence. “Not established” means this source review did not verify availability; it is not a claim that nothing exists.
available
Architecture
The VLA architecture and interfaces are documented.
Inspect this claim’s source ↗available
Inference code
Reference inference and robot integration code is public.
Inspect this claim’s source ↗available
Training code
Fine-tuning and training utilities are public.
Inspect this claim’s source ↗partial
Training recipe
Training and fine-tuning procedures are documented, but full-scale reproduction depends on diverse robot data.
Inspect this claim’s source ↗available
Data information
Embodiments and dataset sources are documented.
Inspect this claim’s source ↗partial
Training data
Substantial open robotics datasets are provided, but not every source used is represented as one corpus.
Inspect this claim’s source ↗partial
Evaluation
Technical evaluations are published; real-world transfer remains platform-dependent.
Inspect this claim’s source ↗partial
Commercial use
NVIDIA permits commercial use under its model terms; dataset-specific permissions remain separate. Custom terms do not by themselves prohibit commercial use.
Inspect this claim’s source ↗WHY THIS RELEASE MATTERS
What to explore.
- Humanoid manipulation
- Cross-embodiment fine-tuning
- Open robotics tooling
WHAT THE RECORD DOES NOT ESTABLISH
Keep the limits.
- Robot results depend on hardware, calibration, and safety controls
- Real-world operation needs physical safeguards
The original GR00T N1 paper provides research evaluation; N1.7 deployment claims remain primarily NVIDIA-reported.
CONNECTED EVIDENCE
A release becomes a starting point.
- A shared starting point for humanoid skills
Isaac GR00T N1.7 is a downloadable vision-language-action model intended as a base for developing humanoid robot skills.
The weights use the NVIDIA Open Model License, which is distinct from an OSI-approved open-source license. Public artifacts do not establish site-specific reliability or physical safety.
Thematic or family connections, not proof that an older application uses the selected checkpoint.
FOLLOW THE RECORD
Sources, not superlatives.
- Isaac GR00T N1.7 release ↗ (repository)
- Isaac GR00T repository ↗ (repository)
- Isaac GR00T platform ↗ (institution)
Source check: 2026-09-19. AI-assisted editorial review, with no named external expert or independent hardware validation claimed. Licenses and model cards can change. Review the linked terms for the specific artifact and intended use.
Understand open source vs open weights ↗