https://www.cnbc.com/2024/03/18/nvidia-announces-gb200-blackwell-ai-chip-launching-later-this-year.html Skip Navigation logo * watchlive logo Markets * Pre-Markets * U.S. Markets * Currencies * Cryptocurrency * Futures & Commodities * Bonds * Funds & ETFs Business * Economy * Finance * Health & Science * Media * Real Estate * Energy * Climate * Transportation * Industrials * Retail * Wealth * Sports * Life * Small Business Investing * Personal Finance * Fintech * Financial Advisors * Options Action * ETF Street * Buffett Archive * Earnings * Trader Talk Tech * Cybersecurity * Enterprise * Internet * Media * Mobile * Social Media * CNBC Disruptor 50 * Tech Guide Politics * White House * Policy * Defense * Congress * Equity and Opportunity CNBC TV * Live TV * Live Audio * Business Day Shows * Entertainment Shows * Full Episodes * Latest Video * Top Video * CEO Interviews * CNBC Documentaries * CNBC Podcasts * CNBC World * Digital Originals * Live TV Schedule Watchlist Investing Club * Trust Portfolio * Analysis * Trade Alerts * Meeting Videos * Homestretch * Jim's Columns * Education * Subscribe * Sign In PRO * Pro News * Pro Live * Full Episodes * Stock Screener * Market Forecast * Options Investing * Chart Investing * Subscribe * Sign In Menu * Make It * select + ALL SELECT + Credit Cards + Loans + Banking + Mortgages + Insurance + Credit Monitoring + Personal Finance + Small Business + Taxes + Help for Low Credit Scores + Investing + SELECT + All Credit Cards + Find the Credit Card for You + Best Credit Cards + Best Rewards Credit Cards + Best Travel Credit Cards + Best 0% APR Credit Cards + Best Balance Transfer Credit Cards + Best Cash Back Credit Cards + Best Credit Card Welcome Bonuses + Best Credit Cards to Build Credit + SELECT + All Loans + Find the Best Personal Loan for You + Best Personal Loans + Best Debt Consolidation Loans + Best Loans to Refinance Credit Card Debt + Best Loans with Fast Funding + Best Small Personal Loans + Best Large Personal Loans + Best Personal Loans to Apply Online + Best Student Loan Refinance + SELECT + All Banking + Find the Savings Account for You + Best High Yield Savings Accounts + Best Big Bank Savings Accounts + Best Big Bank Checking Accounts + Best No Fee Checking Accounts + No Overdraft Fee Checking Accounts + Best Checking Account Bonuses + Best Money Market Accounts + Best CDs + Best Credit Unions + SELECT + All Mortgages + Best Mortgages + Best Mortgages for Small Down Payment + Best Mortgages for No Down Payment + Best Mortgages with No Origination Fee + Best Mortgages for Average Credit Score + Adjustable Rate Mortgages + Affording a Mortgage + SELECT + All Insurance + Best Life Insurance + Best Homeowners Insurance + Best Renters Insurance + Best Car Insurance + Travel Insurance + SELECT + All Credit Monitoring + Best Credit Monitoring Services + Best Identity Theft Protection + How to Boost Your Credit Score + Credit Repair Services + SELECT + All Personal Finance + Best Budgeting Apps + Best Expense Tracker Apps + Best Money Transfer Apps + Best Resale Apps and Sites + Buy Now Pay Later (BNPL) Apps + Best Debt Relief + SELECT + All Small Business + Best Small Business Savings Accounts + Best Small Business Checking Accounts + Best Credit Cards for Small Business + Best Small Business Loans + Best Tax Software for Small Business + SELECT + All Taxes + Filing For Free + Best Tax Software + Best Tax Software for Small Businesses + Tax Refunds + Tax Brackets + Tax Tips + Tax By State + Tax Payment Plans + SELECT + All Help for Low Credit Scores + Best Credit Cards for Bad Credit + Best Personal Loans for Bad Credit + Best Debt Consolidation Loans for Bad Credit + Personal Loans if You Don't Have Credit + Best Credit Cards for Building Credit + Personal Loans for 580 Credit Score or Lower + Personal Loans for 670 Credit Score or Lower + Best Mortgages for Bad Credit + Best Hardship Loans + How to Boost Your Credit Score + SELECT + All Investing + Best IRA Accounts + Best Roth IRA Accounts + Best Investing Apps + Best Free Stock Trading Platforms + Best Robo-Advisors + Index Funds + Mutual Funds + ETFs + Bonds * USA * INTL * watchlive Search quotes, news & videos Watchlist SIGN IN logo Markets Business Investing Tech Politics CNBC TV Watchlist Investing Club PRO Menu Tech Nvidia CEO Jensen Huang announces new AI chips: 'We need bigger GPUs' Published Mon, Mar 18 20244:28 PM EDTUpdated Moments Ago thumbnail Kif Leswing@kifleswing WATCH LIVE Key Points * Nvidia on Monday announced a new generation of artificial intelligence chips and software for running AI models. * The new AI graphics processors are named Blackwell and are expected to ship later this year. * The announcement comes as companies and software makers still scramble to get their hands on the current generation of H100s and similar chips. In this article * NVDA Follow your favorite stocksCREATE FREE ACCOUNT Nvidia CEO Jensen Huang delivers a keynote address during the Nvidia GTC Artificial Intelligence Conference at SAP Center on March 18, 2024 in San Jose, California. Justin Sullivan | Getty Images Nvidia on Monday announced a new generation of artificial intelligence chips and software for running artificial intelligence models. The announcement, made during Nvidia's developer's conference in San Jose, comes as the chipmaker seeks to solidify its position as the go-to supplier for AI companies. Nvidia's share price is up five-fold 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 buying the chips. The new generation of AI graphics processors is named Blackwell. The first Blackwell chip is called the GB200 and will ship later this year. Nvidia is enticing its customers with more powerful chips to spur new orders. Companies and software makers, for example, are still scrambling to get their hands on the current generation of "Hopper" H100s and similar chips. "Hopper is fantastic, but we need bigger GPUs," Nvidia CEO Jensen Huang said on Monday at the company's developer conference in California. Nvidia shares fell more than 1% in extended trading on Monday. The company also introduced revenue-generating software called NIM that will make it easier to deploy AI, giving customers another reason to stick with Nvidia chips over a rising field of competitors. Nvidia executives say that the company is becoming less of a mercenary chip provider and more of a platform provider, like Microsoft or Apple, on which other companies can build software. "Blackwell's not a chip, it's the name of a platform," Huang said. "The sellable commercial product was the GPU and the software was all to help people use the GPU in different ways," said Nvidia enterprise VP Manuvir Das in an interview. "Of course, we still do that. But what's really changed is, we really have a commercial software business now." Das said Nvidia's new software will make it easier to run programs on any of Nvidia's GPUs, even older ones that might be better suited for deploying but not building AI. "If you're a developer, you've got an interesting model you want people to adopt, if you put it in a NIM, we'll make sure that it's runnable on all our GPUs, so you reach a lot of people," Das said. Meet Blackwell, the successor to Hopper Nvidia's GB200 Grace Blackwell Superchip, with two B200 graphics processors and one Arm-based central processor. Every two years Nvidia updates its GPU architecture, unlocking a big jump in performance. Many of the AI models released over the past year were trained on the company's Hopper architecture -- used by chips such as 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 additional processing power will enable AI companies to train bigger and more intricate models, Nvidia said. The chip includes what Nvidia calls a "transformer engine specifically built to run transformers-based AI, one of the core technologies underpinning ChatGPT. The Blackwell GPU is large and combines two separately manufactured dies 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 CEO Jensen Huang compares the size of the new "Blackwell" chip versus the current "Hopper" H100 chip at the company's developer conference, in San Jose, California. Nvidia Amazon, Google, Microsoft, and Oracle will sell access to the GB200 through cloud services. The GB200 pairs two B200 Blackwell GPUs with one Arm-based Grace CPU. Nvidia said Amazon Web Services would build a server cluster with 20,000 GB200 chips. Nvidia said that the system can deploy a 27-trillion-parameter model. That's much larger than even the biggest models, such as GPT-4, which reportedly has 1.7 trillion parameters. Many artificial intelligence researchers believe bigger models with more parameters and data could unlock new capabilities. Nvidia didn't provide a cost 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 whole systems that cost as much as $200,000, according to analyst estimates. Nvidia will also sell B200 graphics processors as part of a complete system that takes up an entire server rack. Nvidia inference microservice Nvidia also announced it's adding a new product named NIM, which stands for Nvidia Inference Microservice, to its Nvidia enterprise software subscription. NIM makes it easier to use older Nvidia GPUs for inference, or the process of running AI software, and will allow companies to continue to use the hundreds of millions of Nvidia GPUs they already own. Inference requires less computational power than the initial training of a new AI model. NIM enables companies that want to run their own AI models, instead of buying access to AI results as a service from companies like OpenAI. The strategy is to get customers who buy Nvidia-based servers to sign up for Nvidia enterprise, which costs $4,500 per GPU per year for a license. Nvidia will work with AI companies like Microsoft or Hugging Face to ensure their AI models are tuned to run on all compatible Nvidia chips. Then, using a NIM, developers can efficiently run the model on their own servers or cloud-based Nvidia servers without a lengthy configuration process. "In my code, where I was calling into OpenAI, I will replace one line of code to point it to this NIM that I got from Nvidia instead," Das said. Nvidia says the software will also help AI run on GPU-equipped laptops, instead of on servers in the cloud. CNBC logo * * * * * * * * Subscribe to CNBC PRO * Subscribe to Investing Club * Licensing & Reprints * CNBC Councils * Select Personal Finance * CNBC on Peacock * Join the CNBC Panel * Supply Chain Values * Select Shopping * Closed Captioning * Digital Products * News Releases * Internships * Corrections * About CNBC * Ad Choices * Site Map * Podcasts * Careers * Help * Contact * News Tips Got a confidential news tip? We want to hear from you. Get In Touch * CNBC Newsletters Sign up for free newsletters and get more CNBC delivered to your inbox Sign Up Now Get this delivered to your inbox, and more info about our products and services. * Advertise With Us Please Contact Us * Privacy Policy * California Consumer Privacy Act (CCPA) Opt-Out Icon * CA Notice * Terms of Service (c) 2024 CNBC LLC. All Rights Reserved. A Division of NBCUniversal Data is a real-time snapshot *Data is delayed at least 15 minutes. Global Business and Financial News, Stock Quotes, and Market Data and Analysis. Market Data Terms of Use and Disclaimers Data also provided byReuters logo comscore