Nvidia has made a significant announcement at CES 2025, unveiling Project Digits, a personal AI supercomputer designed for developers, researchers, and students. This desktop-sized system, priced at $3,000, is capable of handling AI models with up to 200 billion parameters, a remarkable feat considering its compact size and standard power outlet requirements.

The heart of Project Digits is the new GB10 Grace Blackwell Superchip, which packs immense processing power while being energy-efficient. This allows the system to run sophisticated AI models, previously requiring larger and more power-hungry systems. The product's design resembles a Mac Mini, making it a sleek addition to any workspace.

Nvidia CEO Jensen Huang emphasized the significance of Project Digits, stating that it will empower developers, researchers, and students to shape the age of AI. With this system, users can engage with AI in various applications and industries, making it a mainstream technology.

Each Project Digits system comes equipped with 128GB of unified, coherent memory and up to 4TB of NVMe storage. For more demanding applications, two systems can be linked together to handle models with up to 405 billion parameters, rivaling Meta's best model, Llama 3.1. The GB10 chip delivers up to 1 petaflop of AI performance at FP4 precision, making it an incredibly powerful tool for AI development.

The system features Nvidia's latest-generation CUDA cores and fifth-generation Tensor Cores, connected via NVLink-C2C to a Grace CPU containing 20 power-efficient Arm-based cores. MediaTek, a renowned chip design company, collaborated on the GB10's development to optimize its power efficiency and performance.

Users of Project Digits will also gain access to Nvidia's AI software library, including development kits, orchestration tools, and pre-trained models available through the Nvidia NGC catalog. The system runs on Linux-based Nvidia DGX OS and supports popular frameworks like PyTorch, Python, and Jupyter notebooks. Developers can fine-tune models using the Nvidia NeMo framework and accelerate data science workflows with Nvidia RAPIDS libraries.

One of the most significant advantages of Project Digits is its ability to allow users to develop and test their AI models locally, then deploy them to cloud services or data center infrastructure using the same Grace Blackwell architecture and Nvidia AI Enterprise software platform. This seamless transition will streamline the AI development process and make it more accessible to a wider range of users.

This announcement comes on the heels of Nvidia's December release of the Jetson Orin Nano Super, a $249 AI computer targeting hobbyists and startups, capable of handling models up to 8 billion parameters. Project Digits marks a significant step forward in Nvidia's mission to make AI more accessible and mainstream.

The implications of Project Digits are far-reaching, with the potential to democratize AI development and empower a new generation of innovators. As AI continues to transform industries and applications, Nvidia's personal AI supercomputer is poised to play a pivotal role in shaping the future of this technology.