NVIDIA 945-137766-0000-000
NVIDIA Jetson Orin Nano Super Developer Kit
User Manual
Product Overview
The NVIDIA Jetson Orin Nano Super Developer Kit is a compact and powerful computer designed for generative AI applications on small edge devices. It delivers up to 67 TOPS of AI performance, significantly improving upon previous generations, enabling the execution of vision transformers, large language models, and more.
This platform is supported by NVIDIA's comprehensive AI software stack and a broad ecosystem, making it an accessible and affordable solution for developers. Existing users can upgrade their systems with a simple software update to unlock new possibilities in generative AI.
The developer kit includes a Jetson Orin Nano 8GB module and a reference carrier board. This board is designed to accommodate all Orin Nano and Orin NX modules, serving as an ideal platform for prototyping next-generation edge AI products. The Jetson Orin Nano 8GB module features an Ampere GPU and a 6-core ARM CPU, facilitating multiple concurrent AI application pipelines and high-performance inference. The carrier board offers a wide array of connectors, including two MIPI CSI connectors that support camera modules with up to 4-lanes, allowing for higher resolution and frame rates.
Figure 1: The NVIDIA Jetson Orin Nano Super Developer Kit, showcasing its compact design and integrated cooling fan.
The Jetson platform runs the NVIDIA AI software stack, which includes use-case-specific application frameworks such as NVIDIA Isaac for robotics, NVIDIA Metropolis for vision AI, and NVIDIA Holoscan for sensor processing. Developers can also leverage NVIDIA Omniverse Replicator for synthetic data generation (SDG) and NVIDIA TAO Toolkit for fine-tuning pre-trained AI models from the NGC catalog.
A robust ecosystem of partners provides additional AI and system software, developer tools, and custom software development services. These partners can also assist with cameras, other sensors, carrier boards, and design services for product development.
Jetson Orin modules offer unmatched performance and efficiency for robots and autonomous machines, providing the flexibility to create advanced AI solutions using the latest NVIDIA technology. Combined with the industry-standard NVIDIA AI software stack and a comprehensive ecosystem, the path to market for new products is significantly accelerated.
Setup Guide
1. Unboxing and Initial Inspection
Carefully unpack all components from the box. Verify that all items listed below are present and in good condition. If any items are missing or damaged, contact your vendor immediately.
- NVIDIA Jetson Orin Nano Super Developer Kit (main board with module)
- Power Adapter
- Type B (US, JP) Power Cable
- Type I (CN) Power Cable
- Quick Start and Support Guide
Figure 2: The NVIDIA Jetson Orin Nano Developer Kit packaging and main components.
2. Connecting Peripherals
Before powering on the device, connect necessary peripherals. The carrier board provides various I/O options:
- Display: Connect a monitor to the DisplayPort output.
- USB Devices: Connect a keyboard, mouse, and any other USB peripherals to the available USB ports.
- Network: Connect an Ethernet cable to the RJ45 port for wired network access, or ensure Wi-Fi is configured for wireless connectivity.
- Cameras: Utilize the two MIPI CSI connectors for camera modules, supporting up to 4-lanes for higher resolution and frame rates.
Figure 3: Top view of the Jetson Orin Nano Developer Kit, highlighting various ports and connectors for peripherals.
3. Powering On
Connect the appropriate power cable to the power adapter, then plug the adapter into the DC input jack on the Jetson Orin Nano Developer Kit. Finally, plug the power cable into a wall outlet. The system should power on automatically.
Video 1: Product Overview. This video demonstrates the unboxing and initial components of the NVIDIA Jetson Orin Nano Developer Kit, providing a visual guide to its physical aspects and included accessories.
Operating Instructions
1. Software Environment
The Jetson Orin Nano Developer Kit runs on the NVIDIA AI software stack. This includes various frameworks and tools optimized for AI development and deployment.
- NVIDIA JetPack SDK: This is the most comprehensive solution for developing AI applications on Jetson. It includes the Jetson Linux Driver Package (L4T) with a Linux kernel, bootloader, NVIDIA drivers, flashing utilities, sample file system, and toolchains. It also includes libraries for AI, computer vision, and multimedia.
- Application Frameworks:
- NVIDIA Isaac for robotics applications.
- NVIDIA Metropolis for vision AI applications.
- NVIDIA Holoscan for sensor processing.
- Development Tools:
- NVIDIA Omniverse Replicator for synthetic data generation (SDG).
- NVIDIA TAO Toolkit for fine-tuning pre-trained AI models from the NGC catalog.
Refer to the official NVIDIA Jetson documentation for detailed instructions on installing and configuring the software stack.
2. Running AI Applications
The Jetson Orin Nano is designed to run various AI models, including vision transformers and large language models. Its Ampere GPU and multi-core ARM CPU enable efficient inference.
- Model Deployment: Models can be deployed using frameworks like TensorFlow, PyTorch, and ONNX Runtime, optimized with NVIDIA TensorRT for maximum performance.
- Concurrent Pipelines: The hardware supports running multiple AI application pipelines simultaneously, making it suitable for complex edge AI solutions.
- Power Modes: The device supports various power modes to optimize performance and energy consumption based on application requirements. Consult the Jetson documentation for power management settings.
Maintenance
Proper maintenance ensures the longevity and optimal performance of your NVIDIA Jetson Orin Nano Super Developer Kit.
- Cleaning: Regularly clean the device to prevent dust accumulation, especially around the fan and heatsink. Use compressed air to gently clear dust from vents and components. Ensure the device is powered off and disconnected from power before cleaning.
- Ventilation: Ensure the developer kit is placed in a well-ventilated area. Avoid obstructing the fan or air vents, as this can lead to overheating and reduced performance.
- Software Updates: Keep the Jetson Linux Driver Package (L4T) and other NVIDIA software components updated to the latest versions. Updates often include performance improvements, bug fixes, and security patches.
- Environmental Conditions: Operate the device within recommended temperature and humidity ranges to prevent damage to electronic components.
Troubleshooting
This section addresses common issues and provides potential solutions for the NVIDIA Jetson Orin Nano Super Developer Kit.
| Problem | Possible Cause / Solution |
|---|---|
| Limited LLM Performance (e.g., cannot run >8B models) | The Jetson Orin Nano has specific memory and processing limitations. For larger language models, consider optimizing the model, reducing its size, or utilizing techniques like quantization. Ensure sufficient RAM is available by minimizing background processes. Creating a larger swap file (e.g., 8-16GB) can also help manage memory for larger models. |
| SD Card Imaging Issues / SDK Manager Problems |
|
| Docker/Networking Errors (e.g., "failed to set up container networking") | These errors often indicate missing kernel modules or issues with iptables. Ensure your Jetson OS is fully updated. If the issue persists, consult NVIDIA's official forums or documentation for specific kernel module requirements or Docker configuration for Jetson. Recompiling the kernel from source is an advanced solution that may be required in some cases. |
| Difficulty Installing Libraries (e.g., PyTorch, OpenCV with GPU support) | Installation of these libraries with GPU support can be complex. Follow official NVIDIA guides or community-verified tutorials precisely. Incorrect installations can lead to lack of GPU acceleration or obscure errors. Verify CUDA and cuDNN installations are correct and compatible with your library versions. |
| This is a known configuration setting. Refer to the Jetson Linux documentation or community resources for instructions on how to enable Bluetooth audio by modifying the relevant configuration file. | |
| General Steep Learning Curve / System Instability | The Jetson platform is powerful but requires familiarity with Linux and embedded systems. Expect a learning curve. If the system becomes unstable or "bricked," re-flashing the Jetson OS is often the most reliable solution. Always back up important data. Utilize NVIDIA's extensive documentation, developer forums, and community resources for support. |
Specifications
| Feature | Detail |
|---|---|
| Brand | NVIDIA |
| Model Name | Jetson Orin Nano 8GB |
| Item Model Number | 945-137766-0000-000 |
| Processor | Arm® Cortex-A78AE (6-core) |
| GPU | Ampere Architecture |
| AI Performance | Up to 67 TOPS |
| RAM Memory Installed Size | 8 GB |
| Operating System | Linux |
| Wireless Type | Bluetooth |
| Item Weight | 1.7 pounds |
| Product Dimensions (LxWxH) | 3.94 x 3.11 x 0.83 inches |
| Date First Available | March 21, 2023 |
Warranty and Support
The NVIDIA Jetson Orin Nano Super Developer Kit is manufactured by NVIDIA. For specific warranty terms and conditions, please refer to the documentation included with your product or visit the official NVIDIA support website.
Optional protection plans may be available for purchase separately to extend coverage beyond the standard manufacturer's warranty. These plans typically offer additional benefits such as extended repair or replacement services.
For technical support, software downloads, and community forums, please visit the official NVIDIA Developer website for Jetson products. This resource provides comprehensive guides, tutorials, and a platform to connect with other developers.
Related documents945-137766-0000-000
Ask a question about this manual
Ask about setup, troubleshooting, compatibility, parts, safety, or missing instructions. Manuals+ will review the question and use this page’s manual context to help answer it.