By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel consensus is bearish on Nvidia's current valuation, with key concerns being the reliance on sustained hyperscaler spending, potential competition from AMD and custom ASICs, and the risk of multiple compression if growth fails to accelerate beyond current expectations. However, there's a bullish perspective that sovereign demand for AI compute capacity could provide a floor for Nvidia's growth.
Risk: Sustained hyperscaler spending and multiple compression if growth fails to accelerate
Opportunity: Sovereign demand for AI compute capacity
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 growth rate is far greater than most other big techs.
Investors recently received great news about 2027.
There's currently only one company valued at $5 trillion: Nvidia (NASDAQ: NVDA). While that's a huge market cap, I actually think Nvidia is undervalued.
It may seem counterintuitive to say the world's largest company is undervalued, but after digging in a bit, I think you'll see what I mean.
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 has risen to the top thanks to insatiable demand for its graphics processing units (GPUs). It's the undisputed leader in this realm, and its products are the industry standard for AI training and inference. With the AI hyperscalers spending hundreds of billions of dollars on capital expenditures (capex) this year, it shouldn't surprise anyone that the chipmaker's growth continues to be impressive.
In the first quarter, revenue rose 85% year over year to $81.6 billion. That rate is more than the next four largest companies combined. Wall Street analysts project Nvidia to continue this acceleration trend through next quarter, with the average analyst guiding for 96% growth to $91.7 billion.
Those are absurd numbers, yet despite their impressive nature, the company still doesn't draw the same respect as its big tech peers. From the perspective of forward earnings valuation, it has the lowest valuation of the five largest companies in the world.
That makes Nvidia actually look cheap compared to its peers. There is growing concern about what its future looks like, but 2027 will likely be somewhat of a repeat of 2026.
In its conference call, Nvidia's management said it expects data center capex to reach $1 trillion next year from AI hyperscalers. The company likely has some insider information here, as it receives orders for GPUs well in advance so that it can fulfill them when it's time to ship. So, next year should be strong as well.
When you use the forward price-to-earnings ratio (P/E) with projected 2027 earnings, Nvidia's bargain price tag becomes more apparent.
If Nvidia can rise to the same level as its peers, then the stock has at least 50% upside. That would be a solid return in a short time frame, and it showcases just how good a deal investors can get on the stock right now. Just because you missed the initial run-up doesn't mean you have to miss the rest of its rise. Nvidia's stock looks like a solid value right now, and it's time to act.
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 $462,983! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,375,447!
Now, it’s worth noting Stock Advisor’s total average return is 995% — a market-crushing outperformance compared to 212% 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 June 3, 2026. *
Keithen Drury has positions in Alphabet, Amazon, Microsoft, and Nvidia. The Motley Fool has positions in and recommends Alphabet, Amazon, Apple, Microsoft, and 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
"Nvidia's 'discount' valuation reflects appropriate cyclical risk, not hidden upside; the bull case requires flawless execution and sustained hyperscaler capex that the market has already priced in."
The article's 50% upside thesis rests entirely on multiple expansion—NVDA trading at a lower forward P/E than peers (MSFT, GOOGL, AMZN, AAPL) and converging upward. But this misses the core issue: those peers trade at premiums because they have diversified revenue, pricing power, and lower cyclicality. Nvidia's valuation *should* be lower because it's a pure-play cyclical commodity supplier to a handful of hyperscalers. The $1T capex forecast for 2027 is management guidance—not independent verification—and assumes sustained hyperscaler spending without pullback, competition, or demand saturation. The article also ignores that 85-96% YoY growth is already priced in; multiple expansion requires *acceleration* beyond consensus, not just maintenance.
If hyperscalers' ROI on AI capex proves stronger than expected and they commit to $1.5T+ annual spend through 2028, Nvidia's moat widens, gross margins stay elevated, and a 15-16x forward multiple (vs. current ~12x) is defensible—delivering the promised 50% return.
"Nvidia's valuation re-rating thesis hinges on unproven $1T capex materializing without margin or share loss in 2027."
The article highlights Nvidia's 85-96% YoY revenue growth and lowest forward P/E among megacaps, arguing undervaluation via 2027 earnings. Yet it underplays execution risks around the $1T hyperscaler capex forecast, which Nvidia itself projects but cannot control. If AI ROI disappoints or custom ASICs from Google, Amazon, and Microsoft accelerate, growth could decelerate sharply after 2026, compressing multiples even if earnings temporarily beat. Export curbs and competition from AMD further threaten the monopoly narrative the piece assumes will persist.
The $1T capex figure comes directly from Nvidia's management visibility into advance orders, and current hyperscaler spending trajectories support it through at least 2027 without immediate ROI proof needed.
"Nvidia's current valuation relies on unsustainable growth projections that ignore the cyclical nature of semiconductor capital expenditures and the looming risk of hyperscaler ROI fatigue."
The article conflates current revenue velocity with long-term terminal value, a dangerous trap for NVDA investors. While 85% year-over-year growth is undeniable, the market is pricing in a 'perpetual hyper-growth' scenario that ignores the inevitable law of large numbers and the cyclicality of semiconductor capital expenditures. Relying on 2027 projections of $1 trillion in hyperscaler capex assumes a linear adoption curve for AI, ignoring potential saturation or a 'wait-and-see' pivot by cloud providers if ROI on GPU clusters doesn't materialize. NVDA is currently a momentum play disguised as a value play; its forward P/E compression is a reflection of market skepticism regarding the sustainability of these margins, not a discount.
If the hyperscalers' $1 trillion capex spend represents a structural shift in global infrastructure rather than a cyclical build-out, NVDA’s current valuation is merely the floor for an indispensable utility provider.
"The valuation already prices in perpetual AI-enabled growth; a slower-than-expected AI capex cycle or margin compression could trigger a meaningful multiple contraction and a material stock drawdown."
Nvidia’s run is powerful but not guaranteed. The article cites Q1 revenue up 85% to $81.6B and 96% growth next quarter to $91.7B, plus data-center capex nearing $1T, which justifies optimism. However, sustained AI capex and margin expansion depend on a non-stop hyperscaler cycle, which is risky: any slowdown in AI demand, pricing pressure from AMD/Intel, or supply/demand shifts could compress Nvidia’s multiple. Regulatory/geopolitical risks (e.g., export controls affecting China) and capital-intensified competition could also sap the upside. In short, the growth path is credible but fragile; the stock risks a sharp re-rating if the AI boom cools or margins compress.
The bull case rests on an uninterrupted AI capex frenzy and unassailable GPU dominance; history warns that cycles turn, competition bites, and margins normalize—any sign of slower AI adoption or policy constraints could dramatically reprice Nvidia.
"Nvidia's valuation hinges not on capex forecasts but on whether hyperscalers' AI revenue-per-GPU proves durable enough to justify 2027-28 spending without pullback."
Claude and Gemini both flag the 'perpetual hyper-growth' trap, but miss a critical distinction: Nvidia's gross margins (72-75%) are already elevated *and* expanding YoY—not contracting as typical in commodity cycles. If hyperscalers achieve positive ROI on AI capex (measurable by 2025-26), the capex cycle self-sustains structurally rather than cyclically. The real test isn't whether $1T is achievable; it's whether hyperscalers' revenue per GPU dollar justifies continued spend. Nobody addressed this ROI inflection point directly.
"ROI confirmation timing creates a window where growth deceleration triggers de-rating before the bull case validates."
Claude notes expanding margins and ROI as key, yet the 18-24 month lag between capex and measurable AI returns means confirmation arrives after Nvidia's revenue has scaled substantially larger. Sustaining 85%+ growth becomes improbable at that base, risking multiple compression even with stable margins if acceleration fails to materialize beyond 2026.
"Sovereign AI demand provides a non-cyclical demand floor that decouples Nvidia's revenue from hyperscaler ROI skepticism."
Claude and Grok are missing the 'sovereign AI' factor. Hyperscalers are not the only buyers; national governments and energy-rich states are now entering the bidding war for compute capacity to ensure digital sovereignty. This creates a floor for demand that is independent of hyperscaler ROI metrics. If sovereign demand becomes a meaningful revenue pillar, the cyclical 'wait-and-see' pivot by big tech becomes a secondary concern rather than a terminal risk for Nvidia's growth.
"Sovereign demand is not a reliable floor for Nvidia; policy, budget cycles, and export controls can cap pricing and create volatile demand that could compress multiples."
Gemini's 'sovereign AI' floor is intriguing but overstated. Sovereign demand could exist, yet it's highly policy- and budget-driven: capital cycles, export controls (e.g., China), and long-term take-or-pay contracts can cap pricing power and drive sharp demand swings. If governments curb orders or reallocate to domestic vendors, or fiscal cycles tighten, Nvidia's multiple could re-rate lower even with continued data-center growth—making the 'floor' less robust than the piece implies.
The panel consensus is bearish on Nvidia's current valuation, with key concerns being the reliance on sustained hyperscaler spending, potential competition from AMD and custom ASICs, and the risk of multiple compression if growth fails to accelerate beyond current expectations. However, there's a bullish perspective that sovereign demand for AI compute capacity could provide a floor for Nvidia's growth.
Sovereign demand for AI compute capacity
Sustained hyperscaler spending and multiple compression if growth fails to accelerate