ThinkRobotics Edge AI Device with NVIDIA Jetson Orin™ NX 8GB / 16GB module (Dual Ethernet)
ThinkRobotics Edge AI Device is built with Jetson Orin NX 8GB or 16GB - a powerful and compact intelligent edge box to bring up to 100 TOPS modern AI performance to the edge, which offers up to 5X the performance of Jetson Xavier NX and up to 3X the performance of Jetson AGX Xavier. Combining the NVIDIA Ampere™ GPU architecture with 64-bit operating capability, Orin NX integrates advanced multi-function video and image processing, and NVIDIA Deep Learning Accelerators.
The full system includes one NVIDIA Jetson Orin™ NX 8GB or 16GB production module, the Waveshare Jetson Orin IO Base B carrier board, a heatsink, AW-CB375NF Dual-Band Wireless NIC WiFi5 module, and a power adapter installed in a 3D printed carbon fiber case or metal case. The device is preinstalled with JetPack 6.2.2 on the included 240GB NVMe SSD, simplifies development, and fits for deployment for edge AI solution providers working in video analytics, object detection, natural language processing, medical imaging, and robotics across industries of smart cities, security, industrial automation, smart factories.
Features
| AI Performance | On-device processing with up to 100 TOPS AI performance, delivering low power consumption and low latency for production deployments. |
| Form Factor | Hand-size edge AI device (130mm × 120mm × 58.5mm) with NVIDIA Jetson Orin™ NX 16GB/8GB module, integrated cooling fan with heatsink, enclosure, and power adapter. Supports desktop placement and wall mounting. |
| I/O Interfaces | 3× USB 3.2 Gen2, 1× USB 2.0, DisplayPort (4K), 2× CSI camera ports, 1× Gigabit Ethernet + 1× 2.5 Gigabit Ethernet (dual LAN), M.2 Key E (Wi-Fi), M.2 Key M (NVMe), CAN, and GPIO. |
| Software & Storage | Pre-installed NVIDIA JetPack™ 5.1 on 240GB NVMe SSD, includes Linux BSP with support for Jetson ecosystem, AI frameworks, and software platforms. |
| Certifications | FCC, CE, and RoHS certified. |
Description
With rich extension modules, industrial peripherals, and thermal management, this ThinkRobotics device for Jetson is ready to help you accelerate and scale the next-gen AI product by deploying popular DNN models and ML frameworks to the edge and inferencing with high performance, for tasks like real-time classification and object detection, pose estimation, semantic segmentation, and natural language processing (NLP).
We have prepared abundant guides to get started with NVIDIA Jetson using leading AI frameworks and software. For example, with Deepstream and TensorRT, developers can deploy custom YOLOv5 models on Jetson Orin at over 100FPS
Developers Tools
Pre-installed Jetpack for fast development and edge AI integration
Jetson software stack begins with NVIDIA JetPack™ SDK which provides a full development environment and includes CUDA-X accelerated libraries and other NVIDIA technologies to kickstart your development. JetPack includes the Jetson Linux Driver package which provides the Linux kernel, bootloader, NVIDIA drivers, flashing utilities, sample filesystem, and toolchains for the Jetson platform. It also includes security features, over-the-air update capabilities, and much more.
| Category | Platform / Tool | Description |
| Computer Vision & Embedded ML | NVIDIA DeepStream SDK | Streaming analytics toolkit for AI-based multi-sensor processing, video, and image understanding on Jetson. |
| NVIDIA TAO Toolkit | Low-code framework built on TensorFlow and PyTorch to accelerate AI model training. | |
| alwaysAI | Platform to build, train, and deploy computer vision applications with access to 100+ pre-trained models. | |
| Edge Impulse | Embedded ML pipeline for deploying audio, classification, and object detection applications with minimal cloud dependency. | |
| Roboflow | Toolchain for converting images into custom-trained computer vision models and deploying them on Jetson. | |
| YOLOv5 (Ultralytics) | Lightweight object detection model supporting transfer learning with minimal training data. | |
| Deci | Platform to benchmark and optimize runtime performance of AI models on NVIDIA Jetson devices. | |
| Speech AI | NVIDIA Riva | GPU-accelerated SDK for building real-time, customizable speech AI applications. |
| Remote Fleet Management | Allxon | Secure OTA updates and remote device management platform. |
| Robot & ROS Development | NVIDIA Isaac ROS | Hardware-accelerated ROS packages for building high-performance robotics applications on NVIDIA platforms. |
| Cogniteam Nimbus | Cloud-based platform for managing and deploying autonomous robots with Jetson and Isaac support. |
Hardware Overview
Dual Ethernet & Interface-rich Carrier Board
The Waveshare carrier board (Base B) is a high-performance, interface-rich board, providing DisplayPort (4K), Dual Ethernet (1x GbE + 1x 2.5GbE), 3x USB 3.2 Gen 2, 1x USB 2.0, M.2 key E, M.2 key M, CSI camera, CAN, GPIO, I2C, I2S, fan, and other rich peripheral interfaces.
| Module Socket | 260-pin SO-DIMM socket for connecting Jetson Orin Nano / Orin NX modules |
| Control Header | 12-pin header supporting power button, reset button, debug serial port, force recovery, auto power-up enable, and power indicator |
| Power | Power button; DC jack supporting 9V–19V input, compatible with 5.5 × 2.5mm plug |
| Camera | 2 × 22-pin CSI camera interfaces |
| Display | DisplayPort supporting up to 4K output |
| USB (Type-A) | 4 × USB Type-A ports: 3 × USB 3.2 Gen2 (up to 10Gbps), 1 × USB 2.0 (up to 480Mbps) |
| Ethernet | 1 × RJ45 2.5G Ethernet port, 1 × RJ45 Gigabit Ethernet port |
| USB (Type-C) | USB Type-C port for system flashing and data communication |
| Internal Headers | 40-pin header; 4-pin PWM fan header |
| Internal USB | 2 × USB 2.0 connectors |
| FFC Connectors | 0.5mm pitch, 6-pin FFC connectors |
Part List
| NVIDIA Jetson Orin™ NX 8GB / 16GB | x1 |
| Waveshare Carrier Board (Base B) - Dual Ethernet | x1 |
| 240GB NVMe SSD | x1 |
| Aluminum Heatsink with Fan | x1 |
| 3D Printed Case / Aluminium Case | x1 |
| Wi-Fi Module with Antenna | x1 |
| 12V / 5A Power Adapter | x1 |
Documentations
Want to buy in bulk?
Custom Requirements?
Discussion Forum
Feel free to ask questions, share tips or report issues.