Apakah Anda Salah Menjual Nvidia? Ini Yang Diungkapkan GTC 2026 Untuk 2 Tahun ke Depan.

Key Points
Nvidia hopes to do $500 billion in revenue this year -- and then double it.
The stock is down 15% from all-time highs.
- 10 stocks we like better than Nvidia ›
Nvidia (NASDAQ: NVDA) raised eyebrows last year when CEO Jensen Huang estimated that the artificial intelligence (AI) infrastructure opportunity could be worth up to $4 trillion over the next five years. It's reasonable to presume that Nvidia would get a good chunk of that, as its Blackwell and next-generation Rubin graphics processing units are in high demand for their ability to train and run high-level AI applications.
But now investors have more clarity about how much Nvidia expects to generate in revenue and by when. And the answer may surprise you.
Will AI create the world's first trillionaire? Our team just released a report on the one little-known company, called an "Indispensable Monopoly" providing the critical technology Nvidia and Intel both need. Continue »
Speaking at the Nvidia GTC (GPU Technology Conference) in San Jose, California, in mid-March, Nvidia projected it would generate a staggering $1 trillion in AI revenue in the 2027 calendar year, a dramatic increase from its previous estimate of $500 billion during this year.
Nvidia stock is down about 15% from its all-time high, and it's lost roughly $1 trillion in market capitalization since breaking through the $5 trillion barrier last year. A lot of people have dumped Nvidia stock amid fears of an AI bubble.
If you're one of those investors, then I think it's time to get back on the Nvidia freight train. Huang made a valid case at Nvidia GTC that the company still has an amazing opportunity -- and AI will be a tremendous tailwind for Nvidia stock.
What happened at Nvidia GTC?
The big news from Nvidia GTC was the company's sales projections. Nvidia has been bringing in profits hand over fist as graphics processing units (GPUs) are in high demand; sales in the fourth quarter of fiscal 2026 (ending Jan. 25) were $68.1 billion, up 73% from a year ago. Of that, $62.3 billion came from the data center segment, up 75% on a year-over-year basis.
Sales were driven by the company's Blackwell chips, which began shipping in late 2024. And they are expected to be amplified this year when Nvidia begins selling its new Rubin chip, which has greater capabilities and 10x energy efficiency. Huang says it will combine its Rubin chips with storage, inference accelerators, and Ethernet racks to create what he's calling an "AI supercomputer" that will provide a massive step forward for agentic AI solutions.
"Finally, AI is able to do productive work, and therefore the inflection point of inference has arrived," he said.
Agentic AI is the next step in AI evolution, as it can complete tasks and make decisions without constant human intervention. One of the most interesting products using agentic AI is OpenClaw, which integrates with messaging apps to serve as a personal assistant for file management, web browsing, and other tasks. Huang unveiled a new product at Nvidia GTC called NemoClaw, which he says is designed specifically for OpenClaw.
"It finds OpenClaw. It downloads it. It builds you an AI agent," he said.
The company also promoted the Nvidia Groq 3 Language Processing Unit (LPU), the first chip developed following Nvidia’s $20 billion purchase of Groq’s assets in December 2025. Huang said Nvidia is selling a full rack dedicated to the new Groq accelerators that’s designed to work alongside the Rubin rack-scale systems.
The path to $1 trillion
Nvidia’s revenue has exploded higher with the rollout of its GPUs, transforming the hardware company into one of the most consequential of our time. Nvidia’s revenue in the last 12 months was $215.9 billion, and that's already projected to approach $500 billion in the next two years.
So Huang’s projection that Nvidia could more than double that is truly breathtaking. Nvidia is banking on its ability to integrate inference accelerators into its broader AI infrastructure platform, providing a pathway for customers to complete individual computing, inference, agentic AI, storage, and networking tasks, or to work together for a complete turnkey solution.
If you bailed on Nvidia stock during its most recent dip, this is probably a good time to correct that error in judgment while the stock is still in correction territory. I don't think it will be lagging for long.
Should you buy stock in Nvidia right now?
Before you buy stock in Nvidia, consider this:
The Motley Fool Stock Advisor analyst team just identified what they believe are the 10 best stocks for investors to buy now… and Nvidia wasn’t one of them. The 10 stocks that made the cut could produce monster returns in the coming years.
Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you’d have $532,066!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,087,496!*
Now, it’s worth noting Stock Advisor’s total average return is 926% — a market-crushing outperformance compared to 185% for the S&P 500. Don't miss the latest top 10 list, available with Stock Advisor, and join an investing community built by individual investors for individual investors.
*Stock Advisor returns as of April 5, 2026.
Patrick Sanders has positions in Nvidia. The Motley Fool has positions in and recommends Nvidia. The Motley Fool has a disclosure policy.
The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.