Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Jensen Huang, founder, president and CEO of Nvidia, talks about the future of artificial intelligence and its impact on energy consumption and production at the Bipartisan Policy Center in Washington, DC on September 27, 2024.
Chip Somodevilla | Getty Images
Nvidia on Monday revealed new chips for desktop and laptop PCs that use the same Blackwell architecture that underlies the company’s fastest AI processors for servers and data centers.
The chips, called GeForce RTX 50 series, will come preinstalled in computers priced from about $550 to $2,000, the company said. Laptops with the chips will begin shipping in March.
Nvidia unveiled the processors at CES in Las Vegas, where CEO Jensen Huang delivered a keynote on Monday.
“You’ve got this incredible graphics card, Blackwell, I’m going to scale it down and put it in there,” Huang said, holding up the laptop.
Nvidia, which has took off for $3.5 trillion in market capitalization by selling artificial intelligence chips to giant cloud providers and other technology companies, until the last few years was known for selling graphics processing units (GPUs) to power video games. The first Nvidia chip in late 1999 was designed to quickly draw triangles and polygons for 3D games.
“Of course, we were a gaming company at the time, and these GPUs were built to accelerate games,” said Justin Walker, Nvidia’s senior product director, on a press call.
Today, Wall Street is less enthusiastic about Nvidia’s gaming business, given the boom in artificial intelligence and the ever-increasing demand for more computing power. In Art quarter which ended in October, Nvidia’s gaming sales accounted for less than 10% of total revenue, compared with 88% from data center chips.
Nvidia has the vast majority of the data center AI GPU market, outpacing the competition Advanced Micro Devices and Intel.
But CES, formerly known as the Consumer Electronics Show, is all about consumer products, and the new chips announced Monday are mostly for gaming.
Nvidia says the RTX 50-series chips will support a feature called DLSS 4, which uses AI to boost frame rates in games. They can also display character faces with more detail and generally provide users with better graphics and higher resolution.
Nvidia’s gaming business is growing, with revenue up 15% year-over-year in the latest quarter. But data center sales have at least doubled for six consecutive quarters, topping $30 billion in the most recent period.
Nvidia says the technical improvements made for its massive artificial intelligence business will carry over to its gaming graphics cards.
“Even though we’re now an AI company as well as a gaming company, our gaming side still benefits a lot from being an AI company,” Walker said. .
The Blackwell GPU architecture and core design used in the 50-series chips debuted in the company’s AI accelerators, which were announced in March and started shipping at the end of last year. Nvidia said they were designed and optimized for neural networks used by ChatGPT OpenAI and Google Twins.
The new chips for PCs and laptops will come in different configurations. The company says the most expensive and powerful of the chips, the RTX 5090, will sell separately for $1,999 and is twice as fast as its predecessor, the RTX 4090. Nvidia says it has 92 billion transistors, compared to the company’s 208 billion. B200 GPU for servers.
Nvidia says the chips will be optimized to run artificial intelligence and computer graphics models, not just the latest games. The chips will be powerful enough for some game makers to integrate generative artificial intelligence into their characters in games like “PUBG: Battlegrounds.”
The new processors will also be powerful enough to run large language and image generation models from companies including MetaMistral and Stability AI, Nvidia said.
WATCH: Rasgon from Bernstein says investors need exposure to Nvidia
