NVIDIA Jetson Orin Nano 8GB developer kit — 40 TOPS AI, 6-core Arm Cortex-A78AE, 1024-core Ampere GPU, edge AI
The NVIDIA Jetson Orin Nano 8GB Developer Kit is a compact, high-performance edge AI platform delivering up to 40 TOPS (Tera Operations Per Second) of AI compute — making it one of the most powerful small-form-factor AI computers available for robotics, computer vision, and intelligent IoT applications. It is the ideal starting point for developers building next-generation AI-powered products at the edge.
Powered by the Jetson Orin Nano 8GB module, the developer kit features a 6-core Arm Cortex-A78AE CPU, a 1024-core NVIDIA Ampere GPU with 32 Tensor Cores, and 8GB of 128-bit LPDDR5 memory. It runs NVIDIA JetPack SDK, providing full access to CUDA, cuDNN, TensorRT, DeepStream, and the broader NVIDIA AI software ecosystem.
Key Specifications:
- Module: Jetson Orin Nano 8GB
- AI performance: up to 40 TOPS
- CPU: 6-core Arm Cortex-A78AE @ 1.5GHz
- GPU: 1024-core NVIDIA Ampere architecture with 32 Tensor Cores
- Memory: 8GB 128-bit LPDDR5 @ 68 GB/s
- Storage: microSD card slot + M.2 Key M NVMe SSD slot
- Video encode/decode: 1x 4K30 encode, 2x 4K30 decode
- Camera: 2x MIPI CSI-2 connectors (up to 4 lanes each)
- Display: HDMI 2.1 (up to 4K60)
- USB: 4x USB 3.2 Gen2 Type-A, 1x USB-C (data + power)
- Networking: Gigabit Ethernet, M.2 Key E (Wi-Fi/BT optional)
- GPIO: 40-pin expansion header (compatible with Raspberry Pi HATs)
- Power: 5–15W configurable TDP
- SDK: NVIDIA JetPack (CUDA, cuDNN, TensorRT, DeepStream, ROS2)
Key Features:
- 40 TOPS AI performance — run real-time object detection, segmentation, and NLP models at the edge
- NVIDIA Ampere GPU + Tensor Cores — hardware-accelerated deep learning inference with TensorRT
- Full JetPack SDK support — CUDA, cuDNN, TensorRT, DeepStream, Isaac ROS out of the box
- 40-pin GPIO header — compatible with Raspberry Pi HATs and standard maker peripherals
- Dual MIPI CSI-2 camera support — stereo vision, depth sensing, and multi-camera AI pipelines
- NVMe SSD slot — high-speed storage for large AI models and datasets
- 5–15W power envelope — efficient edge deployment without active cooling requirements at low power modes
Applications:
- Robotics — autonomous navigation, manipulation, and perception
- Computer vision — object detection, face recognition, defect inspection
- Edge AI inference — on-device LLM, image classification, pose estimation
- Smart cameras and video analytics
- Drone and UAV AI payload processing
- Industrial automation and quality control
- Research and AI prototyping
Note: microSD card not included — minimum 64GB UHS-I recommended for JetPack OS. NVMe SSD not included. Wi-Fi/Bluetooth requires optional M.2 Key E module. Power supply (5V/4A USB-C) not included. Flash JetPack OS using NVIDIA SDK Manager or pre-flashed microSD image. Refer to NVIDIA Jetson Orin Nano developer kit getting started guide for initial setup.