Palit, one of Nvidia's main partners in the global graphics card market, has been a key supplier for over 30 years. Primarily recognized for its range of Nvidia GeForce graphics cards, the company is now taking a step into artificial intelligence with Pandora, a mini PC device designed for edge AI computing.
Pandora Features
Pandora is a compact device with dimensions of 121 mm x 145 mm x 66 mm and a weight of 470 g. Although it looks like a mini PC, it is specifically designed for AI inference, machine learning acceleration, and robotics tasks.
Hardware Specifications
- Nvidia Jetson Orin NX Super platform
- Versions with 8GB or 16GB RAM
- Performance up to 157 AI TOPS
- Pre-installed with Ubuntu Linux and JetPack SDK 6.1.1
- Active cooling system to maintain performance under load
Connectivity and Ports
Pandora includes a varied selection of ports, ideal for connecting peripherals and legacy devices:
- Two USB 3.2 Gen2 Type-A ports
- One USB 3.2 Gen2 Type-C/OTC port
- Two USB 2.0 Type-A ports
- Two Ethernet ports (2 x RJ45, 1G)
- One HDMI 2.0 port
- Line Out/Line In audio options via 3.5mm jack or pin header
Custom Expansion
One of Pandora's standout features is its ability to support 3D-printed expansions through customizable cases. This option is especially useful for developers who need adaptable hardware.
“Pandora is ideal for applications that require versatile and high-performance hardware for edge AI tasks,” commented a Palit spokesperson.
Pandora Applications
Palit suggests several use cases for Pandora, highlighting its versatility across different sectors:
- Smart Retail: Customer demographics analysis to display personalized real-time ads through digital screens.
- Education: Interactive tools like object recognition and text-to-speech technology.
- Robotics and Automation: Extensive I/O options and compatibility with Nvidia Isaac and ROS2.
- Generative AI: Support for demanding tasks like natural language processing and content creation.
With Pandora, Palit not only aims to offer a compact device but to expand the capabilities of developers and companies that need efficient and scalable AI solutions.