Nvidia already sells large quantities of computer chips to all the major companies that build proprietary artificial intelligence models. But now, at a time when public interest in open source and DIY AI is increasing, the company announced that it will also begin offering a “personal AI supercomputer,” which starts at $3,000 by the end of this year and that anyone can use in their own home. own home or office.
Nvidia’s new desktop computer, called Digits, goes on sale in May and is about the size of a small book. It contains an Nvidia “super chip” called GB10 Grace Blackwell optimized to speed up the calculations needed to train and run AI models, and comes equipped with 128GB of unified memory and up to 4TB of NVMe storage to handle especially large AI programs.
Jensen Huang, founder and CEO of Nvidia, announced the new system, along with several other AI offerings, during a keynote speech today at CES, an annual conference for the computer industry in Las Vegas (you can check out all the announcements most important). on the WIRED CES live blog).
“Placing an AI supercomputer on the desks of every data scientist, AI researcher and student allows them to participate in and shape the AI era,” Huang said in a statement released ahead of his keynote speech.
Nvidia says the Digits machine, which stands for “deep learning gpu intelligence training system,” will be able to run a single large language model with up to 200 billion parameters, a rough measure of a model’s complexity and size. To do this today, you would need to rent space from a cloud provider like AWS or Microsoft, or build a custom system with a handful of chips designed to run AI. If two Digits machines are connected via a proprietary high-speed interconnect link, Nvidia says they will be able to run the most capable version available of Meta’s open-source Llama model, which has 405 billion parameters.
The digits will make it easier for hobbyists and researchers to experiment with models that approach the basic capabilities of OpenAI’s GPT-4 or Google’s Gemini in their offices or basements. But the best versions of those proprietary models, housed inside giant data centers owned by Microsoft and Google, are probably bigger and more powerful than anything Digits could handle.
Nvidia has been one of the biggest beneficiaries of the AI boom. Its share price has soared in recent years as technology companies clamored to buy large quantities of the advanced hardware chips it produces, a crucial ingredient for developing cutting-edge AI. The company has proven itself adept at optimizing hardware and software for AI, and its product roadmap has become an important sign of where the industry is expected to go next.
When launched, Digits will be the most powerful consumer computing hardware Nvidia offers. It already sells a range of chipsets for AI development known as Jetson that start at about $250. These can run smaller AI models and be used as a mini desktop computer or installed on a robot to test different AI programs.