Features

• Powered by the NVIDIA Jetson Orin Nano module with Super Mode enabled, a compact edge AI computer built for AI inferencing at the edge
• Onboard 4GB or 8GB, 64-bit / 128-bit LPDDR5 memory, configurable to match the AI workload
• M.2 M-Key 2280 NVMe slot for configurable onboard storage, up to 128GB
• GbE LAN with PoE/PSE support, USB 3.1 Type-A, RS-485 serial ports, and CAN-FD for industrial connectivity
• HDMI 2.0 display output and SIM card slot for cellular connectivity
• Wide operating temperature range, -20°C to 50°C, suited for industrial and outdoor AI camera deployments
• Fanless, compact embedded form factor with DIN rail, wall mount, or VESA mounting compatible for flexible installation
• Wi-Fi and 4G/5G expansion via M.2 E-Key and B-Key slots
• 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): 4GB / 8GB

Capability

• Runs real-time object detection, person detection, and basic video analytics on a single camera feed, suited for AI-powered surveillance and smart monitoring
• Delivers up to 67 TOPS of AI inference performance in Super Mode, enough for lightweight computer vision models at the edge
• Decodes video up to 4K60 H.265, supporting high-resolution IP camera streams for video analytics
• Handles entry-level edge computing tasks like automated number plate recognition (ANPR), people counting, and intrusion detection
• Software-based video encoding on CPU, adequate for occasional streaming, not built for continuous multi-stream video encoding
• Runs one AI model at a time efficiently, not designed for multi-model concurrent inferencing
• Low power footprint, up to 25W system draw, makes it viable for solar-powered, battery-backed, or remote edge AI deployments

Target Users

Embedded developers and system integrators building cost-sensitive, single-camera setups. Common deployments: automated toll systems, entry-level inspection drones, basic retail monitoring, small industrial IoT gateways, and early-stage robotics prototyping.