NVIDIA Jetson Nano is an embedded system-on-module (SoM) and developer kit from the NVIDIA Jetson family, including an integrated 128-core Maxwell GPU, quad-core ARM A57 64-bit CPU, 4GB LPDDR4 memory, along with support for MIPI CSI-2 and PCIe Gen2 high-speed I/O.
Useful for deploying computer vision and deep learning, Jetson Nano runs Linux and provides 472 GFLOPS of FP16 compute performance with 5-10W of power consumption.
Technical Blog — NVIDIA Jetson Nano Brings AI to Everyone
- 1 Jetson Nano Developer Kit
- 2 Software Support
- 3 Guides and Tutorials
- 4 Ecosystem Products and Sensors
- 5 Getting Help
Jetson Nano Developer Kit
The Jetson Nano Developer Kit is an easy way to get started using Jetson Nano, including the module, carrier board, and software. It costs $99 and is available from distributors worldwide.
- 80x100mm Reference Carrier Board
- Jetson Nano Module with passive heatsink
- Pop-Up Stand
- Getting Started Guide
(the complete devkit with module and heatsink weighs 138 grams)
What You Will Need
- Power Supply
- MicroSD card (16GB UHS-1 recommended minimum)
Ports & Interfaces
- 4x USB 3.0 A (Host)
- USB 2.0 Micro B (Device)
- MIPI CSI-2 x2 (15-position Camera Flex Connector)
- HDMI 2.0
- Gigabit Ethernet (RJ45)
- M.2 Key-E with PCIe x1
- MicroSD card slot
- (3x) I2C, (2x) SPI, UART, I2S, GPIOs
- Follow the Getting Started with Jetson Nano Guide to setup your devkit and format the MicroSD card.
- Plug in an HDMI display into Jetson, attach a USB keyboard & mouse, and apply power to boot it up.
- Visit the Embedded Developer Zone and Jetson Nano Developer Forum to access the latest documentation & downloads.
The devkit is available for $99 from the NVIDIA webstore and global distributors, including:
For the full list, refer to the Region Selector.
Guides and Tutorials
This section contains recipes for following along on Jetson Nano.
- Hello AI World (jetson-inference)
- TensorFlow 1.13.1 Installer (pip wheel)
- PyTorch 1.1 Installer (pip wheel)
- MXNet 1.4 Installer (pip wheel)
- Deep Learning Inference Benchmarking Instructions
- TensorFlow Object Detection With TensorRT (TF-TRT)
- RidgeRun's GstInference
- RidgeRun's R2Inference
See the NVIDIA AI-IoT GitHub for other coding resources on deploying AI and deep learning.
- NVIDIA JetBot (AI-powered robotics kit)
- jetbot_ros (ROS nodes for JetBot)
- ROS Melodic (ROS install guide)
- ros_deep_learning (jetson-inference nodes)
Ecosystem Products and Sensors
The following are 3rd-party accessories, peripherals, and cameras available for Jetson Nano.
- e-con Systems e-CAM30_CUNANO (3.4 MP MIPI Camera)
- Logitech C920 (USB webcam)
- Leopard Imaging LI-IMX219-MIPI-FF-NANO (IMX219 sensor)
- Raspberry Pi Camera v2 (IMX219 sensor)
- Stereolabs ZED (stereo camera)
- Antmicro Jetson Nano Baseboard (module carrier)
- Auvidea JN30 (module carrier)
- Auvidea JN30-LC (module carrier)
- ConnectTech Nano-Pac (3D-printable enclosure)
- Jetson Nano Case (3D-printable enclosure)
- Jetson NanoMesh (3D-printable enclosure)
- Jetson NanoMesh Mini (3D-printable enclosure)
- jetson_nano_enc (3D-printable enclosure)
- Geekworm Jetson Nano Case (metal enclosure)
See the Power Supply section for more information about selecting proper power adapters.
See the Jetson Nano Supported Components List for devices that have been qualified by NVIDIA to work with Jetson Nano.
If you have a technical question or bug report, please visit the Jetson Nano Developer Forum and search or start a new topic.
See the official Support page on Embedded Developer Zone for warranty and RMA information.