Nvidia already sells large quantities of computer chips to every major manufacturing company artificial intelligence Model. But now, at a time when the public is interested in open source And do-it-yourself AI is growing rapidly, with the company announcing that it will also begin offering a “personal AI supercomputer” later this year, priced starting at $3,000, that anyone can build in their own home. Or can use in office.
Nvidia's new desktop machine, called Digits, will go on sale in May and is the size of a small book. It includes an Nvidia “superchip” called the GB10 Grace Blackwell, which is optimized to accelerate the calculations needed to train and run AI models, and specifically to handle larger AI programs, with 128 gigabytes of integrated memory and 4 Equipped with terabytes of NVMe storage.
Nvidia founder and CEO Jensen Huang announced the new system along with several other AI offerings during a keynote today. cesAn annual conference for the computer industry held in Las Vegas. (You can see all the big announcements here Wired CES Live Blog,
“Putting an AI supercomputer on the desk of every data scientist, AI researcher and student helps them engage and shape the era of AI,” Huang said in a statement released ahead of his keynote address.
Nvidia says the Digit machine, which stands for “Deep Learning GPU Intelligence Training System,” will be able to run a single large language model with 200 billion parameters, which is a rough measure of a model's complexity and size. To do this today, you have 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 the two Digit machines are connected using a proprietary high-speed interconnect link, Nvidia says they will be able to run most capable An open source version of the Llama model is available, containing 405 billion parameters.
The points will make it easier for hobbyists and researchers to experiment with models that come closer to basic capabilities OpenAI's GPT-4 Or Google's Gemini In their offices or basements. But the best versions of those proprietary models, housed inside the giant data centers owned by Microsoft and Google, are probably bigger and more powerful than anything Digital can handle.
Nvidia has been one of the biggest beneficiaries of this AI boomIts stock price has skyrocketed over the past few years as tech companies rush to buy large quantities of the advanced hardware chips it produces, a key component to developing cutting-edge AI. The company has proven to be adept at creating hardware and software optimized for AI, and its product road map has become an important indicator of where the industry is expected to move forward.
When it is released, Digit will be the most powerful consumer computing hardware ever offered by Nvidia. It already sells a line of chipsets called Jetson for AI development that start at around $250. These can run small AI models and can either be used like mini desktop computers or installed on robots to test various AI programs.