Nvidia’s new era of computing is already well underway.
In a gangbusters earnings call on Wednesday, Nvidia CEO Jensen Huang laid out an accelerated timeline for the deployment of Blackwell, the company’s newest AI chip that is twice as fast as Nvidia’s current iteration and boasts five times the AI performance.
Huang unveiled the Blackwell chip earlier this year in March, but the company has been working on its production for some time now, he said this week.
During the question-and-answer portion of the quarterly call, Huang said production shipments of Blackwell will start in the second quarter and ramp up in Q3. According to Huang, customers should have data centers up and running by the fourth quarter.
“We will see a lot of Blackwell revenue this year,” Huang said during the call.
The company’s hot streak doesn’t appear to be slowing anytime soon. Nvidia stock surged to record highs on Wednesday afternoon following first-quarter earnings results, which saw the chip maker report a 262% surge in year-over-year revenues.
“We are poised for our next wave of growth,” Huang said, citing the Blackwell platform.
But even as Huang offered a bullish perspective on Blackwell, excitement for the coming chip doesn’t seem to be killing demand for Nvidia’s current hardware.
“We see increasing demand of Hopper through this quarter,” Huang said, adding that he expects demand to outstrip supply for “some time” as Nvidia transitions to Blackwell.
Blackwell systems have been designed to be “backwards compatible” with Hoppers for an easy transition from one to the other, Huang said Wednesday.
The next-generation graphics processor will cost between $30,000 and $40,000 per unit, Huang said back in March.
But even as Nvidia courts unparalleled success, possible challenges loom ahead, as competitors work tirelessly to develop rival chips, Business Insider reported ahead of Wednesday’s call.