By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel's net takeaway is that while Nvidia's past performance has been exceptional, its future growth trajectory is uncertain and overpriced, with significant risks such as custom ASICs, AI capex slowdown, and margin-mix problems.
Risk: Margin-mix problem due to growing sovereign demand and deteriorating hyperscaler ROI
Opportunity: Geopolitical tailwind from sovereign AI demand
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
Nvidia's revenue has grown 2,500% over the last decade.
Its stock has grown 27,000% since 2016.
Nvidia (NASDAQ: NVDA) is widely considered the most dominant "pick-and-shovel" maker in the artificial intelligence (AI) gold rush. Indeed, if you asked an AI chatbot, like Gemini or Claude, a question today, there's a good chance Nvidia's technology was doing most of the heavy lifting to provide you with an answer.
The company makes super-fast brains for computers (called graphics processing units, or GPUs) that help teach AI how to think. Since no other company's chips compare to Nvidia's, the chipmaker's sales have been growing like weeds.
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 »
Nvidia's full-year revenue in 2025 was $130 billion. Not only is that larger than the GDPs of over 100 countries, but it's also 2,500% higher than its 2016 revenue ($5 billion).
How did Nvidia stock fare over that 10-year period?
Mightily good, if you ask me. In 2016, the company had a market cap of about $20 billion. Today, it boasts the world's highest market cap at more than $5 trillion -- a staggering 27,000% increase from a decade ago.
If you had had the foresight to invest $5,000 in Nvidia 10 years ago, you would be a millionaire today. You would have also crushed almost every other megacap tech stock over that same stretch.
Truth be told, Nvidia isn't richly valued. The stock trades at about 24 times forward earnings, which is only slightly higher than the average for tech stocks (22.7).
It's a stock that continues to surprise. And with AI tailwinds blowing strong, Nvidia may still have a ways to go.
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 $471,827! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,319,291!
Now, it’s worth noting Stock Advisor’s total average return is 986% — a market-crushing outperformance compared to 207% 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 May 10, 2026. *
Steven Porrello has positions in Microsoft and Nvidia. The Motley Fool has positions in and recommends Alphabet, Amazon, Apple, Meta Platforms, Microsoft, Nvidia, and Tesla. 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.
Four leading AI models discuss this article
"Nvidia's current valuation assumes a linear continuation of hyperscaler spending that is fundamentally unsustainable at this scale."
This article is a classic example of survivorship bias disguised as investment advice. While Nvidia’s 27,000% run is historic, anchoring current decisions to past performance is dangerous. The claim that NVDA is 'not richly valued' at 24x forward earnings is deceptive; it ignores the massive capital expenditure cycles of hyperscalers like Microsoft and Google, which are currently inflating Nvidia’s top line. If AI infrastructure spending hits a plateau or if custom silicon initiatives from major cloud providers gain real traction, that 24x multiple could contract sharply as growth normalizes. Investors are paying for a perpetual growth trajectory that rarely persists once a company reaches a $5 trillion market cap.
The bear case ignores that Nvidia is effectively building the 'operating system' for the next industrial revolution, and as long as AI remains a capital-intensive arms race, their pricing power remains untouchable.
"Nvidia's moat faces credible erosion from custom chips and capex scrutiny, with the article's rosy valuation and market cap figures not aligning with current data."
Nvidia's decade-long revenue surge from $5B to a projected $130B FY2025 is undeniable, driven by AI GPU dominance, turning a $5K investment into over $1.3M. However, the article inflates today's market cap at $5T (actual ~$3.3T as of late 2024) and understates forward P/E at 24x (consensus ~35x FY2026 EPS of ~$4/share). It glosses over rising risks: hyperscalers like Google (TPUs), Amazon (Trainium), and Meta building custom ASICs to cut Nvidia reliance; potential AI capex slowdown if ROI lags; AMD's MI300X gaining share. Motley Fool's exclusion of NVDA from their top 10 underscores caution amid priced-for-perfection dynamics.
If AI training/inference demand explodes further with no viable competitors matching Nvidia's CUDA ecosystem efficiency, 50%+ annual growth could easily re-rate multiples higher, extending the rally.
"NVDA's 24x forward P/E assumes sustained double-digit growth in a market where custom silicon and competition are accelerating, but Q4 2025 guidance signals deceleration — the stock is pricing perfection, not optionality."
This article is retrospective marketing dressed as analysis. Yes, NVDA returned 27,000% — but that's survivorship bias. The article conflates past performance with future opportunity while burying the real tension: NVDA trades at 24x forward earnings, only slightly below tech average, despite commanding 80%+ of the high-end GPU market. Revenue growth of 2,500% over a decade is extraordinary, but it's decelerating (Q4 2025 guidance suggests single-digit sequential growth). The 'AI tailwinds' framing ignores that NVDA's moat depends on sustained R&D spending, no credible competitor emerging, and customers not vertically integrating (AMD, Intel, and now Microsoft/Google custom chips are real threats). The article's closing pivot to 'we found 10 better stocks' is a sales funnel, not analysis.
NVDA's installed base in data centers is so dominant and sticky that even modest market-share erosion still leaves a $3+ trillion company; the real risk isn't valuation collapse but 15-20% downside from peak if growth disappoints, not 70%+.
"Valuation is vulnerable to multiple compression if AI demand normalizes or macro cycles slow, despite near-term tailwinds."
While the piece highlights Nvidia's explosive growth and 'AI tailwinds,' it glosses over risks that could derail the bull case. Nvidia trades around 24x forward earnings with peak growth baked in; a material slowdown in hyperscale data-center spend, a cyclical AI capex peak, or policy/regulatory clamps (export controls to China) could curb demand for GPUs. Competitive pressure from AMD/Intel and potential shifts to specialized ASICs or alternative software hardware stacks could erode Nvidia's CUDA moat. If margin expansion stalls or supply-chain constraints bite, the stock's multiple may reprice, even as earnings grow more modestly. Not a one-way ride.
But the strongest counterargument is that AI demand could stay robust longer than expected, with CUDA/related software monetizing beyond hardware, helping sustain pricing power and possibly keeping multiples elevated even if unit sales slow.
"Sovereign AI demand provides a non-commercial floor for Nvidia's revenue that mitigates the risk of a hyperscaler capex pullback."
Grok and Claude correctly identify the ASIC threat, but you are all ignoring the 'sovereign AI' factor. National governments are now buying H100s and Blackwell clusters to ensure domestic AI capability, creating a demand floor independent of hyperscaler ROI metrics. This geopolitical tailwind acts as a hedge against the domestic capex slowdown you all fear. Nvidia isn't just selling to tech giants anymore; they are selling to the state, which is far less price-sensitive.
"Sovereign AI demand is too small, discounted, and offset by local alternatives to meaningfully hedge hyperscaler slowdown."
Gemini, sovereign AI is a red herring—governments like UAE and Saudi Arabia are subsidizing local GPU alternatives (e.g., via Cerebras or AMD partnerships) and demanding volume discounts on H100s, contributing negligibly to revenue (enterprise/sovereign ~15% of Q3 DC sales vs 85% hyperscalers). No real hedge if MSFT/AMZN capex plateaus; it's speculative tailwind at best.
"Sovereign AI demand could mask revenue stagnation while compressing margins, creating a false growth narrative."
Grok's 15% sovereign/enterprise figure deserves scrutiny—that's still ~$2B annualized at current run rates, and geopolitical fragmentation is accelerating, not slowing. But Grok's core point stands: governments are price-sensitive and actively funding alternatives. The real risk nobody flagged: if sovereign demand grows while hyperscaler ROI deteriorates, Nvidia faces a margin-mix problem—selling more units at lower ASPs to less-profitable customers. That's worse than flat revenue.
"Sovereign demand is not a durable floor; export controls and price concessions could erode Nvidia's margin mix, making the 'sovereign tailwind' less reliable and risking multiple compression even if GAAP growth slows."
Gemini's sovereign demand floor is plausible but not durable. Governments can subsidize or stockpile while extracting price concessions, localization, or contract terms that pressure NVDA margins. Export controls to China and potential rollouts of domestic accelerators could cap addressable growth, forcing a mix shift toward lower-margin buyers. If hyperscaler ROI deteriorates even as sovereign demand rises, the net effect could be margin compression and a lower multiple, not a guaranteed floor.
The panel's net takeaway is that while Nvidia's past performance has been exceptional, its future growth trajectory is uncertain and overpriced, with significant risks such as custom ASICs, AI capex slowdown, and margin-mix problems.
Geopolitical tailwind from sovereign AI demand
Margin-mix problem due to growing sovereign demand and deteriorating hyperscaler ROI