Features

• Powered by the NVIDIA Jetson AGX Orin module, a high-performance edge AI computer for demanding inferencing and perception workloads
• Onboard 32GB or 64GB LPDDR5 memory, configurable for large AI model deployment
• M.2 M-Key 2280 NVMe slot for configurable local storage
• Multiple I/O interfaces including GbE LAN, 10GbE LAN, USB 3.2, RS-232/422/485 serial ports, CAN-FD, and HDMI 2.0 for industrial data collection
• Wide range DC power input, 9 to 36 VDC, suited for vehicle-mounted and industrial power systems
• Rugged fanless embedded design with wall mount installation for factory and outdoor AI deployment
• Ships preloaded with NVIDIA JetPack (Linux for Tegra), including CUDA, cuDNN, TensorRT, and DeepStream SDK drivers and libraries, along with configured client applications, ready to deploy out of the box.

Configuration

Memory (select): 32GB / 64GB

Capability

• Processes 16 or more camera streams at once without dropping frames, built for large-scale video management systems (VMS)
• Runs large AI models locally, including 13-billion parameter LLMs, for on-device generative AI and language processing
• Fuses camera, LiDAR, and radar data in real time, enabling full sensor fusion perception stacks for autonomous machines
• Delivers up to 275 TOPS of AI compute, among the highest inferencing performance available in an embedded edge AI computer
• Handles continuous, heavy AI workloads without throttling, built for 24/7 industrial automation and autonomous vehicle operation
• Suited for autonomous guided vehicles (AGVs), robotic surgery assistance, and off-highway autonomous mining equipment
• Positioned for decision-making at the edge, not just detection, enabling machines to act on real-time AI inference

Target Users

Factory automation engineers, autonomous vehicle developers, and heavy industry system designers. Common deployments: autonomous guided vehicles, large-scale video management systems, robotic surgery assistance, autonomous trucking, and mining vehicle perception stacks.