By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel generally agreed that Nvidia's $10T valuation is uncertain and depends on several assumptions, with most panelists expressing skepticism about its sustainability.
Risk: Margin compression due to price wars, custom silicon competition, and potential power rationing.
Opportunity: Sustained capex spending and potential premium pricing due to CUDA's switching costs and the 'Sovereign AI' shift.
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 →
Key Points
Demand for Nvidia's powerful processors continues to grow.
A $10 trillion market cap is in reach if AI demand persists for a couple more years.
- 10 stocks we like better than Nvidia ›
Nvidia (NASDAQ: NVDA) is currently the world's largest company, with a market cap of $4.4 trillion. However, I think that over the next three years, it could grow to $10 trillion.
If that view proves accurate, Nvidia would be a no-brainer stock to buy at today's prices.
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 »
The math for a megacap to more than double
Nvidia grew to its current massive size thanks to insatiable demand for its artificial intelligence (AI) processors. Companies cannot get enough of its computing units, which allows it to charge premium prices and book massive profits. And demand doesn't seem to be slowing down.
Nvidia projects that annual global data center capital expenditures will rise to $3 trillion to $4 trillion by the end of 2030. With the big four AI hyperscalers -- Meta Platforms, Microsoft, Amazon, and Alphabet -- spending around $650 billion on capex this year, there's still a massive runway for growth. For 2025, Nvidia estimated that total data center spending would be around $600 billion, and estimating that this spending will double in 2026 seems to make sense based on what the hyperscalers' projections are telling us.
Nvidia's growth lines up with this projection for the most part, as analysts' consensus estimate is for its revenue to rise around 70% this year. While it's likely that its growth will moderate with each passing year, we're nowhere near the totals that the company believes we will hit.
But how long will it take Nvidia to hit a $10 trillion market cap if this growth rate continues? First, we need to set a reasonable valuation. Because the company is a top-notch executor, I think valuing it at 30 times earnings is fair. So it would need to produce an annual net income of $300 billion. Nvidia's profit margin has consistently hovered about the 50% mark, indicating it would need to generate about $600 billion in revenue to reach a $10 trillion market cap.
When could that happen? It might be fairly soon.
If Nvidia's revenue grows at a 70% pace in its fiscal 2027 (which will end in late January 2027) as Wall Street estimates, its top line will hit $368 billion. If it grows at a 30% pace for the next two years, that will increase to over $620 billion, more than surpassing the $600 billion threshold.
With that in mind, Nvidia has the growth catalysts to easily reach a $10 trillion market cap at a reasonable valuation in the near future. That would also indicate the stock would more than double in three years, making it a no-brainer buy today.
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 $495,179!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,058,743!*
Now, it’s worth noting Stock Advisor’s total average return is 898% — a market-crushing outperformance compared to 183% 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 March 23, 2026.
Keithen Drury 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.
Four leading AI models discuss this article
"The $10T thesis depends entirely on Nvidia maintaining 30% revenue growth AND a 30x P/E through 2028, but neither is guaranteed if competition or demand destruction accelerates."
The math here is mechanically sound but rests on three fragile assumptions: (1) Nvidia sustains 30% revenue growth for two consecutive years after 70% in FY2027—a deceleration that's plausible but not guaranteed; (2) a 30x P/E multiple holds despite NVDA's size and inevitable margin compression as competition intensifies; (3) the $3-4T datacenter capex forecast materializes without demand destruction, regulatory headwinds, or efficiency breakthroughs that reduce chip requirements. The article conflates *available market* with *Nvidia's capture rate*. AMD, Intel, and custom silicon are real. Most critically: $10T implies NVDA captures ~20% of global GDP growth—a structural ceiling that the article never addresses.
If AI capex growth stalls (due to underwhelming ROI, regulatory crackdowns, or a recession), or if customers shift to cheaper alternatives or in-house chips, Nvidia's margin profile collapses faster than revenue, and a 30x multiple becomes indefensible—potentially pricing in a $5-6T cap, not $10T.
"The article ignores the inevitable transition from infrastructure build-out to ROI-focused capital discipline, which will likely force a valuation multiple contraction for Nvidia."
The $10 trillion valuation thesis relies on a linear extrapolation of hyper-growth that ignores the law of large numbers and the inevitable maturation of the data center cycle. While Nvidia (NVDA) dominates the AI hardware stack, projecting $600 billion in revenue by 2028 assumes the hyperscalers—Meta, Microsoft, Amazon, and Alphabet—can sustain current capital expenditure levels without a commensurate surge in AI-driven monetization. We are currently seeing a transition from 'build-out' to 'ROI-justification' phases. If these companies fail to demonstrate clear revenue uplift from AI, the current capex spending spree will face a sharp contraction, compressing Nvidia’s margins and shattering the 30x P/E multiple assumption.
If generative AI achieves true agentic autonomy within two years, the total addressable market for compute could expand exponentially, rendering current revenue projections conservative rather than optimistic.
"N/A"
[Unavailable]
"Hyperscaler custom ASICs and margin erosion make $620B revenue by FY2029 at 50% margins unrealistic, capping NVDA below $8T by 2028."
The article's $10T NVDA thesis hinges on revenue hitting $620B by FY2029 (70% growth to $368B in FY2027, then 30% annually), 50% net margins, and 30x P/E—implying ~2.3x market cap expansion from $4.4T. This overlooks hyperscalers' custom AI chips (e.g., Google's TPUs, Amazon's Trainium/Inferentia, Microsoft's Maia) capturing share from Nvidia's GPUs, plus potential margin compression to 40% as Blackwell ramps and competition intensifies. China export curbs already cap ~20% of data center sales. AI capex may peak by 2027 if ROI disappoints, stalling growth below 30%. Realistic path: $7-8T cap by 2028 at 25x.
If AI inference demand surges 10x as Nvidia claims and Blackwell/Rubin deliver flawless supply, Nvidia could sustain 50%+ margins and GPU monopoly, easily hitting $600B+ revenue by 2029.
"Capex may not contract; instead, ASP erosion + inference shift to custom silicon compresses Nvidia's margin profile while revenue plateaus at $400-450B, not $600B."
Gemini flags the ROI-justification inflection—valid. But all three of you assume capex *contracts* if ROI disappoints. That's backwards. If hyperscalers see weak returns, they'll *accelerate* spend to chase scale economies and amortize sunk costs faster. The real risk: capex stays elevated but *Nvidia's ASP collapses* as customers negotiate harder and custom silicon captures inference workloads. Revenue holds; margins crater. That's the $7-8T scenario Grok sketched, but the mechanism is price compression, not volume collapse.
"Nvidia's software ecosystem (CUDA) provides a pricing moat that prevents the margin collapse predicted by the panel."
Claude, you’re missing the power of the ecosystem moat. You assume Nvidia is a commodity hardware vendor vulnerable to price wars, but CUDA creates massive switching costs that protect ASPs even as custom silicon scales. The real risk isn't margin compression via negotiation; it's the 'Sovereign AI' shift. If governments and non-hyperscalers prioritize domestic compute, Nvidia’s reliance on a few hyperscalers diminishes, potentially sustaining premium pricing longer than your model allows.
[Unavailable]
"Datacenter power constraints will bottleneck NVDA growth well before ROI or competition issues."
Everyone assumes capex sustains or accelerates amid ROI doubts, but ignores the grid's hard limit: hyperscalers need 50GW+ by 2030 (McKinsey est.), yet US interconnection queues exceed 2TW backlog with 5-7yr waits. Nuclear SMRs won't scale fast enough. NVDA's Blackwell revenue—projected 40% of FY2028—faces power rationing first, not chip supply. $10T requires electricity miracle; caps at $6-7T even if demand roars.
The panel generally agreed that Nvidia's $10T valuation is uncertain and depends on several assumptions, with most panelists expressing skepticism about its sustainability.
Sustained capex spending and potential premium pricing due to CUDA's switching costs and the 'Sovereign AI' shift.
Margin compression due to price wars, custom silicon competition, and potential power rationing.