By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
Despite strategic positioning in AI infrastructure, Nvidia's investments in CoreWeave and Coherent pose significant risks, including high leverage, potential dilution, and regulatory scrutiny.
Risk: CoreWeave's refinancing risk and potential follow-on funding, which could amplify downside and impact Nvidia's cash flow.
Opportunity: Nvidia's strategic control over AI infrastructure and ecosystem, ensuring supply chain bottlenecks do not throttle GPU revenue growth.
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 →
While Nvidia's main business is designing chips and other artificial intelligence infrastructure, it also invests some of its capital in public and private companies.
Most of Nvidia's investments are in companies with which it has partnerships, such as suppliers and customers.
Following Nvidia's investments can provide insight into how the company at the center of AI views certain parts of the AI ecosystem.
While investors know Nvidia (NASDAQ: NVDA) as the chipmaker at the center of the artificial intelligence (AI) universe, the company also invests in other companies, several of which are publicly traded.
These are typically other AI companies that Nvidia partners with or that are key suppliers or customers.
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 investment portfolio swelled close to $18.4 billion at the end of the first quarter of this year. During this time, Nvidia plowed $3.8 billion into two AI stocks: one it already owned and the other a new position.
In the quarter, Nvidia increased its stake in the AI data center company CoreWeave (NASDAQ: CRWV) by 95%. Its position in the company increased by more than $1.9 billion at the end of the quarter, bringing the total position to more than $3.65 billion.
Nvidia and CoreWeave have long had a partnership, as CoreWeave purchases graphics processing units (GPUs) from Nvidia and deploys them in its data centers to rent compute to companies looking to deploy AI solutions.
In January, the companies announced they had expanded their relationship in order for CoreWeave to accelerate the construction of more than 5 gigawatts of AI data centers by 2030. Data center build-out is key to the AI revolution, so it's in Nvidia's interest to see CoreWeave grow.
Along with the announcement, Nvidia said it had invested $2 billion into Class A shares of CoreWeave at an average cost of $87.20 per share. Now owning more than 47 million shares, Nvidia's stake is close to 9% in the company.
While CoreWeave is one of the larger data center companies and is likely to continue to benefit as long as AI remains strong, the company's balance sheet is a bit worrisome. Building data centers is a capital-intensive business, and CoreWeave is highly leveraged. It has significantly diluted shareholders' equity.
At the end of the first quarter, CoreWeave's total debt-to-equity ratio, a measure of default risk, was high at 5.2. The company's total liabilities-to-equity ratio, which focuses more on overall leverage, was also very high at 10.6.
The company's outstanding share count has also more than doubled over the past year, driven by multiple private offerings, typically involving convertible notes that can eventually be converted into shares.
I'm not a huge fan of CoreWeave due to these balance sheet issues and the growing competition in the space. If the AI trade does take a turn for the worse, CoreWeave could take a big hit.
In March, Nvidia also announced a new partnership with Coherent (NYSE: COHR). Coherent is a leader in photonics, making components like lasers and optical transceivers that are becoming increasingly important for AI infrastructure.
Nvidia and Coherent's non-exclusive agreement involves a multibillion-dollar purchase commitment from Nvidia and future access and capacity rights to Coherent's advanced laser and optical networking products. The partnership also includes a $2 billion investment from Nvidia to support research and development.
Coherent's products have become important to Nvidia as data centers scale to thousands of GPUs, which require more and more data movement between GPUs before that data is eventually fed into the GPUs.
Specifically, Nvidia uses Coherent's silicon photonics to build Spectrum-X switches. These Ethernet networking platforms are key for "building multi-tenant, hyperscale AI clouds," according to Nvidia.
Coherent is similar to Micron. While Micron differs in that it provides memory that sits on GPUs and feeds them data, both companies have become key components of the AI supply chain, especially as the industry scales.
Coherent's stock has been on a big run, rising nearly 370% over the past year. The stock also trades at close to 70 times forward earnings, although at a more manageable 10.5 times forward revenue.
This is also another stock that will likely live and die with the AI trade, but seems to be in a good spot at the moment. I think investors can take a small position right now, but should wait for pullbacks to add at better entry points or practice dollar-cost averaging to build the position more slowly.
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 $463,900! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,294,401!
Now, it’s worth noting Stock Advisor’s total average return is 978% — a market-crushing outperformance compared to 211% 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 31, 2026. *
Bram Berkowitz has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Coherent, Micron Technology, 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
"CoreWeave's extreme leverage and dilution create downside that Nvidia's stake does not fully offset."
Nvidia's $3.8B Q1 outlays—doubling its CoreWeave stake to $3.65B (9% ownership) and launching a $2B Coherent partnership—map its AI infrastructure bets beyond silicon. CoreWeave's data-center build-out aligns with Nvidia's GPU sales, but 5.2x debt-to-equity and 10.6x liabilities-to-equity plus rapid dilution flag refinancing risk if hyperscale capex pauses. Coherent's silicon photonics role in Spectrum-X switches supports scaling, yet 70x forward earnings embeds aggressive AI growth assumptions. Investors should watch whether these positions buffer or amplify sector volatility when AI ROI metrics are tested.
Nvidia's guaranteed GPU purchases and capacity rights could stabilize CoreWeave's cash flows enough to service debt, turning leverage into an advantage rather than a trap.
"Nvidia's investments reveal not ecosystem strength but dependency risk: CoreWeave and Coherent only win if the AI capex cycle sustains indefinitely, making them leveraged bets on a single thesis rather than diversified hedges."
Nvidia's $3.8B deployment into CoreWeave and Coherent signals confidence in AI infrastructure scaling, but the article buries critical red flags. CoreWeave's 5.2x debt-to-equity and 10.6x liabilities-to-equity ratios are distress-level leverage for a capital-intensive business facing intensifying competition from hyperscalers building in-house. Coherent at 70x forward P/E is pricing in flawless execution during a potential AI capex normalization cycle. The real risk: Nvidia is investing in companies whose survival depends on sustained GPU demand growth—if that inflects, these positions crater regardless of partnership depth. The article frames this as validation; it's actually Nvidia hedging concentration risk by betting on its own ecosystem.
If Nvidia is confident enough to deploy $3.8B, maybe the market is underpricing the durability of AI infrastructure demand, and these positions signal a multi-year capex supercycle that justifies current valuations across the stack.
"Nvidia is using its balance sheet to force-multiply its ecosystem, effectively acting as an internal venture arm to prevent supply-side constraints from stalling its core GPU business."
Nvidia’s capital allocation strategy is less about 'investing' and more about vertical integration and ecosystem control. By funneling billions into CoreWeave and Coherent, Nvidia is essentially subsidizing its own demand and ensuring supply chain bottlenecks—specifically in data center build-outs and optical networking—do not throttle its GPU revenue growth. While the article highlights balance sheet risks at CoreWeave, it misses the strategic necessity: Nvidia is buying insurance against a cooling AI capex cycle. If CoreWeave fails, Nvidia’s own revenue trajectory hits a wall. This isn't a portfolio; it's a defensive moat built with cash to guarantee that the hardware ecosystem remains tethered to Nvidia’s proprietary standards.
Nvidia’s heavy reliance on these partners creates a 'circular dependency' where their growth is artificially inflated by Nvidia’s own capital, potentially masking a lack of organic, end-user demand for AI compute.
"Nvidia's ecosystem bets on CoreWeave and Coherent offer strategic advantages but carry meaningful downside if leverage, valuations, or AI demand soften."
NVDA's two 2026 bets—CoreWeave and Coherent—signal strategic positioning beyond chip design: Nvidia wants to lock in the AI infra backbone by owning or financing key suppliers and customers. Yet the risk is real: CoreWeave's debt-to-equity of 5.2 and total liabilities-to-equity of 10.6 imply a fragile balance sheet if data-center build-out slows or funding costs rise. Coherent trades at about 70x forward earnings, a rich multiple that relies on relentless data-center momentum. The article glosses over liquidity risk, potential dilution from private raises, and how a softer AI cycle could reprice the entire ecosystem.
If AI capex stays robust and these private bets scale smoothly, Nvidia's ecosystem leverage could compound, delivering outsized returns and stronger demand for Nvidia hardware. The upside may far exceed the implied risks.
"CoreWeave leverage converts Nvidia's ecosystem bets into potential repeated capital calls rather than a stable moat."
Gemini's defensive moat thesis ignores the feedback loop where CoreWeave's 5.2x debt-to-equity forces Nvidia into follow-on funding rounds if capex slows, amplifying rather than containing downside. This dynamic links directly to Claude's distress ratios but introduces escalation risk absent from one-time partnership framing. A pause in hyperscaler spending would then hit Nvidia's own cash flow via both direct exposure and lost GPU pull-through.
"CoreWeave's leverage is not a mutual risk—it's Nvidia's contingent liability disguised as a portfolio position."
Grok's follow-on funding escalation risk is real, but misses the asymmetry: Nvidia can absorb CoreWeave dilution without existential pressure—CoreWeave cannot absorb Nvidia withdrawal. The feedback loop runs one direction. More pressing: nobody flagged that CoreWeave's 10.6x liabilities-to-equity likely includes Nvidia's own credit facilities or guarantees, making the leverage ratio a Nvidia liability repackaged as CoreWeave's problem. If CoreWeave refinances at higher rates, Nvidia eats the cost indirectly.
"Nvidia's capital-intensive support for CoreWeave invites significant regulatory risk that could trigger antitrust scrutiny and de-rate the stock."
Claude is right about the hidden liabilities, but missing the antitrust angle. If Nvidia's capital support for CoreWeave is effectively a 'captive customer' scheme, regulators will eventually scrutinize these off-balance-sheet arrangements. This isn't just financial risk; it's a potential regulatory trap. We are assuming these deals are purely strategic, but they look increasingly like artificial demand propping. If the FTC or DOJ investigates these 'partnerships' as anticompetitive, the valuation premium on NVDA will evaporate instantly.
"CoreWeave’s refinancing risk is the underappreciated near-term danger that could trigger dilution and pull-through weakness before any AI capex cycle stabilizes."
Gemini, antitrust concerns are valid but the more immediate risk nobody flags is CoreWeave’s refinancing cycle. If hyperscale capex slows, leverage could force follow-on funding, worsening Nvidia’s dilution and shrinking its GPU pull-through just as demand softens. Regulators could weigh in on the funding structure, but even absent a ruling, the balance-sheet fragility creates a near-term credit signal that could reprice Nvidia’s ecosystem bets.
Despite strategic positioning in AI infrastructure, Nvidia's investments in CoreWeave and Coherent pose significant risks, including high leverage, potential dilution, and regulatory scrutiny.
Nvidia's strategic control over AI infrastructure and ecosystem, ensuring supply chain bottlenecks do not throttle GPU revenue growth.
CoreWeave's refinancing risk and potential follow-on funding, which could amplify downside and impact Nvidia's cash flow.