VLAHardware: Max8 Hz · TensorRT INT8

OpenVLA grasping

Open-source VLA model for manipulation — no proprietary checkpoints.

About this demo

OpenVLA (7B parameter open Vision-Language-Action model) running on Jetson Thor-series modules for general-purpose grasping. Fine-tune on your own teleop data. Inspired by Jetson AI Lab Research Group's OpenVLA review.

Highlights

→Open weights (no proprietary lock-in)
→Fine-tunable on consumer GPU
→TensorRT-optimized export
→Drop-in replacement for proprietary VLAs

Supported robots

Any 6-DoF arm

Related demos

View all →

VLA

GR00T VLA pick-and-place

Language-conditioned manipulation with NVIDIA GR00T N1.5.

Open demo →VLA

VLM agent in Isaac Sim

Vision-language reasoning over a simulated robotics scene.

Open demo →Teleop

CockPit

Predefined teleop dashboard with dual cameras, 3D model, map, and controls.

Open demo →