Nvidia offers a range of similar devices in the same accessibility style — in December, it announced a $249 version of its Jetson computer for AI applications, targeting hobbyists and startups, called the Jetson Orin Nano Super (it handles models up to 8 billion parameters ).

Nvidia founder and CEO Jensen Huang had an extensive CES 2025 address, detailing everything from Nvidia’s next set of GPUs, its plans for embracing the next era of robotics and automotive innovation,

Nvidia announced a new $3,000 PC-sized AI supercomputer for researchers and enterprises that can run ChatGPT locally. It is scheduled for release in May.

Project DIGITS includes 128GB of unified memory and up to 4TB of NVMe storage, making it capable of handling AI models with as many as 200 billion parameters. By linking two DIGITS systems via NVIDIA ConnectX networking, users can push this capability further, managing models with up to 405 billion parameters.

This silicon features a Blackwell GPU connected via NVLink-C2C to an Nvidia Grace CPU. The latter features 20 power-efficient Arm cores for general computing. One of the things that sets AI accelerators apart from gaming GPUs is the memory,