- Pandora is a ‘mini AI hardware’ stuck in a mini PC form factor
- It uses Nvidia’s Jetson Orin NX Super platform
- Comes with 128GB SSD and a Ubuntu OS, in a chassis under 500g
Nvidia’s largest add-in-board partner, Palit, has been a key supplier in the global video card market for over 30 years. Best known for its range of Nvidia GeForce graphics cards, the company is now branching into AI with Pandora, a compact mini PC device built for edge AI computing.
Pandora (announced in a YouTube video spotted by Videocardz) measures just 121mm x 145mm x 66mm and weighs 470g. Although it resembles a mini PC, the new device is described as “mini AI hardware” and is designed specifically for tasks like AI inference, machine learning acceleration, and robotics.
Powered by the Nvidia Jetson Orin NX Super platform, Pandora is available in two versions with 8GB or 16GB of RAM, delivering 117 and 157 AI TOPS respectively. The device comes pre-installed with a 128GB SSD, Ubuntu Linux, and JetPack SDK 6.1.1, and features an active cooling system to maintain performance under load.
Good selection of ports
Pandora sports two USB 3.2 Gen2 Type-A ports, one USB 3.2 Gen2 Type-C/OTC port, and two USB 2.0 Type-A ports for peripherals and legacy devices. It also includes dual Ethernet ports (2 x RJ45, 1G) and an HDMI 2.0 port. For audio, there are both Line Out/Line In options via a 3.5mm jack or pin header.
Through its M.2 slots, users can add SSDs, Wi-Fi, Bluetooth, and 5G/LTE modules. One of Pandora’s standout features is its support for 3D-printed expansions via customizable casing shells, allowing users to extend the device’s capabilities – a handy option for developers in need of adaptable hardware.
Palit suggests several use cases for Pandora. In smart retail, the device can analyze customer demographics to deliver real-time personalized advertisements through digital signage.
In education, it supports interactive teaching tools using object recognition and text-to-speech technology, and for robotics and automation, it provides extensive I/O options and compatibility with Nvidia Isaac and ROS2. It can also handle demanding generative AI tasks such as natural language processing and content creation.
Pricing and release details for Pandora have yet to be announced, but we should know more soon.
