Nvidia announces GB200 Blackwell AI chip to be released later this year

Nvidia on Monday announced a new generation of AI chips and AI model management software. The announcement, made at Nvidia’s developer conference in San Jose, comes as the chipmaker looks to solidify its position as a leading supplier for AI companies.

Nvidia’s stock price has risen fivefold and total sales have more than tripled since OpenAI’s ChatGPT kicked off the AI ​​boom in late 2022. Nvidia’s high-end server GPUs are essential for training and deploying large AI models. Companies like Microsoft and Meta have spent billions of dollars to buy the chips.

The new generation of AI GPUs is called Blackwell. Blackwell’s first chip is called the GB200 and will ship later this year. Nvidia is luring its customers with more powerful chips to spur new orders. Companies and software makers, for example, are still struggling to get their hands on the current generation of “Hopper” H100 and similar chips.

“Hopper is fantastic, but we need bigger GPUs,” Nvidia CEO Jensen Huang said Monday at the company’s developer conference in California.

Shares of Nvidia fell more than 1% in extended trading on Monday.

The company also unveiled a monetization software called NIM that will make it easier to implement AI, giving customers another reason to stick with Nvidia’s chips over a growing field of competitors.

Nvidia executives say the company is becoming less of a chip supplier for hire and more of a platform provider, like Microsoft or Apple, on which other companies can build software.

“Blackwell is not a chip, it’s the name of a platform,” Huang said.

“The commercial product that could be sold was the GPU, and the software was meant to help people use the GPU in different ways,” Nvidia enterprise vice president Manuvir Das said in an interview. “Of course we still do that. But what’s really changed is that now we really have a commercial software business.”

Das said Nvidia’s new software will make it easier to run programs on any of Nvidia’s GPUs, even older ones that may be better suited for implementing but not building AI.

“If you’re a developer, you have an interesting model that you want people to adopt, if you put it in NIM, we’ll make sure it can run on all our GPUs, so you reach a lot of people,” Das said.

Every two years, Nvidia updates its GPU architecture, unlocking a big leap in performance. Many of the AI ​​models released this past year were trained on the company’s Hopper architecture — used by chips like the H100 — which was announced in 2022.

Nvidia says Blackwell-based processors like the GB200 offer a huge performance upgrade for AI companies, with 20 petaflops in AI performance versus 4 petaflops for the H100. The extra processing power will allow AI companies to train larger and more complex models, Nvidia said.

The chip includes what Nvidia calls a “transformer engine specifically designed to drive transformer-based AI, one of the core technologies behind ChatGPT.

The Blackwell GPU is large and combines two separately manufactured matrices into one chip manufactured by TSMC. It will also be available as an entire server called the GB200 NVLink 2, combining 72 Blackwell GPUs and other Nvidia parts designed to train AI models.

Nvidia said the system can implement a model with 27 trillion parameters. This is much larger than even the largest models, such as GPT-4, which is said to have 1.7 trillion parameters. Many AI researchers believe in larger models with more parameters and data can unlock new possibilities.

Nvidia didn’t provide pricing for the new GB200 or the systems it’s used in. Nvidia’s Hopper-based H100 costs between $25,000 and $40,000 per chip, with entire systems costing up to $200,000, according to analyst estimates.