By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
Despite Nvidia's significant investment, CoreWeave's high capital intensity, dependence on Nvidia chips, and potential competition from hyperscalers' custom silicon pose significant risks. The company's ability to maintain profitability and convert backlog into revenue is uncertain.
Risk: High capital intensity and potential competition from hyperscalers' custom silicon
Opportunity: Nvidia's strategic investment and potential supply chain control
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 →
The rapid adoption of AI has opened the floodgates for neocloud operators.
Nvidia nearly doubled its stake in CoreWeave compared to Q4, owning roughly 11% of the company.
Nvidia's encouragement, combined with CoreWeave's explosive growth and improving profit potential, creates an intriguing opportunity.
Artificial intelligence (AI) has been on a blistering run over the past several years, and its adoption shows no signs of slowing. These cutting-edge algorithms promise to change the technology landscape as we know it, and it's been a windfall for companies at the forefront of this technology. Nowhere is that more apparent than in Nvidia (NASDAQ: NVDA).
The AI-centric chipmaker pioneered the graphics processing units (GPUs) that create lifelike images in video games. Those same processors are now the gold standard for powering AI, making Nvidia the de facto flag-bearer for the technology.
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 »
In the first quarter, Nvidia effectively doubled its position in CoreWeave (NASDAQ: CRWV), prompting investors to take a fresh look at the neocloud operator.
Cloud computing became widely available more than two decades ago, providing businesses with on-demand computing services. Neoclouds are the latest version of these services, offering GPU-as-a-service (GPUaaS) and AI-as-a-Service (AIaaS). CoreWeave is the largest and most well-known of these neocloud providers.
CoreWeave has a strategic partnership with Nvidia, giving the company something of a competitive advantage. By collaborating with Nvidia, CoreWeave has access to the company's most recent state-of-the-art AI chips.
Nvidia already had a sizable position in CoreWeave, owning more than 24.2 million shares. According to a regulatory filing released after the market close on Friday, Nvidia nearly doubled its holdings in the first quarter, bringing its total stake to more than 47.2 million shares. In all, Nvidia owns roughly 11% of CoreWeave's outstanding stock, a stake currently worth $4.9 billion and 20% of the chipmaker's equity portfolio.
When he announced the investment earlier this year, Nvidia CEO Jensen Huang expounded on the opportunity, saying:
CoreWeave's deep AI factory expertise, platform software, and unmatched execution velocity are recognized across the industry. Together, we're racing to meet extraordinary demand for Nvidia AI factories -- the foundation of the AI industrial revolution.
Given Nvidia's growing ties to CoreWeave and its massive vote of confidence, should investors follow suit?
CoreWeave's growth is compelling. In the first quarter, revenue surged 112% year over year to $2 billion, while its loss per share was essentially flat at $1.40.
Perhaps as important is the company's backlog, which surged 284% year over year to $99.4 billion, which provides insight into future revenue. In fact, CEO Michael Intrator said on the earnings call that "demand is accelerating across the board."
As CoreWeave continues to expand to meet unrelenting demand, the company is investing heavily in capital expenditures (capex), with 2026 spending expected to range from $31 billion to $35 billion. Despite the heavy investment, CoreWeave said, "Our deployments continue to be profitable at the contract level." This suggests that as the company scales, the profits will likely come.
CoreWeave isn't yet profitable, but it did keep the red ink static in the first quarter. Value investors will likely take a hard pass at the company's lack of profits, despite its stellar growth. That said, the stock is selling for roughly 8 times sales, down from its mid-2025 peak of 27 times sales. On the other hand, Nvidia -- which is highly profitable -- and selling for just 27 times forward earnings, gives investors another way to play the AI boom.
That said, Nvidia's mentorship, combined with the company's accelerating revenue growth, might make it worth owning a small stake in CoreWeave as part of a balanced portfolio.
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 $469,293! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,381,332!
Now, it’s worth noting Stock Advisor’s total average return is 993% — 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 18, 2026. *
Danny Vena, CPA 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
"CoreWeave's growth story hinges on Nvidia's continued dominance, but rising capex and hyperscaler competition make profitability far from assured."
Nvidia's near-doubling of its CoreWeave stake to 11% and $4.9B underscores its bet on GPUaaS demand, with CoreWeave's Q1 revenue jumping 112% to $2B and backlog hitting $99.4B. Yet this masks extreme concentration risk: CoreWeave depends almost entirely on Nvidia chips and AI factory builds, while projecting $31-35B capex in 2026 with persistent losses. Hyperscalers like Amazon and Microsoft are rapidly expanding their own GPU capacity, potentially eroding neocloud pricing power. Investors chasing the Nvidia endorsement overlook how quickly AI infrastructure spending can pivot if enterprise ROI disappoints.
Nvidia's direct operational partnership and equity stake could secure CoreWeave preferential access to scarce H100/H200 supply, turning the $99B backlog into durable high-margin revenue that justifies the capex ramp.
"CoreWeave's backlog and revenue growth mask a company that will require $100B+ in cumulative capex before reaching sustainable profitability, making it a capital sinkhole rather than an AI opportunity."
Nvidia's 11% stake in CoreWeave is being framed as validation, but it's actually a warning flag dressed as endorsement. CoreWeave is burning cash at scale—$31-35B capex in 2026 against $2B quarterly revenue means the company is in a capital intensity death march. The 284% backlog growth sounds impressive until you realize backlogs aren't revenue and don't guarantee margins. CoreWeave trades at 8x sales (down from 27x) because the market is pricing in massive dilution ahead. Nvidia's investment isn't mentorship; it's Nvidia ensuring supply chain lock-in while offloading infrastructure risk onto public shareholders.
If CoreWeave achieves contract-level profitability at scale and capex growth moderates post-2026, the backlog converts to durable high-margin revenue, and the stock re-rates upward—making Nvidia's stake a genuine strategic win, not a capital trap.
"Nvidia’s investment in CoreWeave acts as a synthetic demand-generation engine that masks potential saturation risks in the broader cloud infrastructure market."
Nvidia’s increased stake in CoreWeave is less about portfolio diversification and more about strategic supply chain control. By bankrolling a 'neocloud' operator, Nvidia is essentially creating a captive customer base to absorb its H100/B200 GPU supply, ensuring high utilization rates for its hardware. While the article highlights a $99.4 billion backlog, investors must recognize this is highly concentrated. If hyperscalers like AWS or Azure significantly ramp their own internal silicon or optimize their existing GPU clusters, CoreWeave’s 'contract-level profitability' could evaporate under the weight of its $30B+ annual capex requirements. Nvidia is essentially hedging against a slowdown in traditional cloud spending by subsidizing its own ecosystem's infrastructure.
Nvidia’s investment could be viewed as a desperate attempt to prop up a primary customer that lacks the balance sheet resilience of a Microsoft or Google to survive a cyclical downturn in AI demand.
"Nvidia's CoreWeave stake could accelerate the AI infra cycle by locking in a growth partner with favorable chip access, but the real test is CoreWeave's ability to turn its backlogs into sustainable profits while capex remains outsized."
Nvidia nearly doubling its stake in CoreWeave to ~11% signals a deliberate bet on neocloud GPUs becoming a core AI infra layer. The move may accelerate Nvidia’s platform monetization by deepening integration with a fast-growing, capital-heavy client, while giving CoreWeave a potential partner-friendly ramp in chip supply and software. Yet the story hinges on fragile math: CoreWeave isn’t profitable yet, backlog is massive but non-binding cash flow until deployments materialize, and 2026 capex guidance of $31-35B implies ongoing burn even as revenue climbs. Valuations look stretched for a private business, and any slowdown in AI demand or chip pricing pressure could sap upside.
The hype could be mispriced; CoreWeave's backlog may be contingent; Nvidia's bet on a private, capital-intensive operator could disappoint if GPU demand normalizes.
"Hyperscaler custom chips could trigger CoreWeave price cuts by mid-2025 before backlog monetizes."
Gemini links the stake to supply absorption but underplays the timing risk: hyperscalers' custom silicon ramps could force CoreWeave into price cuts by mid-2025 before its $99B backlog converts. At 8x sales with $31-35B capex ahead, any 10-15% ASP decline would widen losses faster than Nvidia's H100 priority can offset, turning the endorsement into a shared downside trap rather than a hedge.
"Contract structure and workload segmentation matter more than commodity ASP risk in evaluating CoreWeave's downside."
Grok's ASP-decline scenario is concrete, but misses CoreWeave's contract lock-in defense: most backlog is likely multi-year fixed-price deals signed at 2024 rates. Hyperscaler custom silicon (AWS Trainium, Azure Maia) targets inference, not training—CoreWeave's core margin driver. The real risk isn't 2025 price pressure; it's whether CoreWeave's capex ROI materializes if enterprise AI adoption stalls, not ASP compression from competitive silicon.
"Nvidia is using CoreWeave to artificially manage supply and prevent a GPU price collapse, masking underlying demand weakness."
Claude, your reliance on 'fixed-price' backlog is dangerous; these contracts often include 'most-favored-customer' clauses that force price adjustments if market rates drop. You also ignore the secondary market: if hyperscalers flood the market with underutilized H100s, CoreWeave’s utilization rates will crater regardless of contract status. Nvidia isn't just hedging; they are creating a 'shadow inventory' to prevent a GPU glut from crashing their ASPs. This is a supply-side management play, not a growth investment.
"Backlog and capex optimism hinges on demand; the 'shadow inventory' approach risks margin compression if hyperscalers ramp own silicon and utilization declines."
Gemini's 'shadow inventory' thesis hinges on Nvidia sustaining GPU utilization through subsidized demand, but backlog isn't cash flow and 2026 capex guidance of $31-35B magnifies downside risk if demand softens. If hyperscalers deploy more own silicon and utilization falls, CoreWeave could see margin compression or higher losses despite fixed-price deals, undermining the upside to Nvidia's stake and suggesting the risk isn’t a GPU glut so much as a demand-growth trap.
Despite Nvidia's significant investment, CoreWeave's high capital intensity, dependence on Nvidia chips, and potential competition from hyperscalers' custom silicon pose significant risks. The company's ability to maintain profitability and convert backlog into revenue is uncertain.
Nvidia's strategic investment and potential supply chain control
High capital intensity and potential competition from hyperscalers' custom silicon