Bởi Maksym Misichenko · Nasdaq ·
Các tác nhân AI nghĩ gì về tin tức này
The panel largely agrees that Sandisk's current high margins and valuation are unsustainable due to the volatile nature of the memory market and potential supply increases from competitors. However, there's debate on whether Sandisk can maintain pricing power through long-term contracts or by pivoting to high-margin AI-specific memory.
Rủi ro: Potential supply increases from competitors like Samsung and SK Hynix, which could flood the market and collapse prices.
Cơ hội: Potential for Sandisk to maintain high margins through long-term contracts or by successfully pivoting to high-margin AI-specific memory.
Phân tích này được tạo bởi đường dẫn StockScreener — bốn LLM hàng đầu (Claude, GPT, Gemini, Grok) nhận các lời nhắc giống hệt nhau với các biện pháp bảo vệ chống ảo tưởng tích hợp. Đọc phương pháp →
Sandisk is posting substantial sequential growth.
Sandisk is sold out of memory products through 2026, and tech giants are rushing to buy its 2027 production in advance.
A Melius Research report forecasts that memory demand will remain elevated for the rest of the decade.
Sandisk (NASDAQ: SNDK) has been the top-performing S&P 500 stock over the past year, rising by about 4,200%. Its market cap has blasted past $240 billion, and based on its parabolic growth, a $1 trillion valuation may be realistic within the next five years.
Indeed, it may hit that milestone even earlier; fellow memory storage provider Micron (NASDAQ: MU) accomplished the feat recently, thanks to a surge of more than 800% over the past year. Sandisk has been growing faster than Micron in recent quarters, and both have long-term tailwinds.
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 »
High sequential growth has been the main story that has helped Sandisk gain market cap so rapidly since it was spun back off from Western Digital in February 2025. In its fiscal 2026 third quarter (which ended April 3), Sandisk's revenue increased by 97% sequentially to $5.95 billion. Sandisk only brought in $1.7 billion in the prior-year period.
The NAND flash drive provider is riding the artificial intelligence (AI) wave. Grand View Research projects that the AI industry will grow at a compound annual rate of 30.6% through 2033. Sandisk has already been an outsized beneficiary of that trend, and its guidance implies high sequential growth will continue: The company is aiming for $8 billion at the midpoint for the fourth quarter of its fiscal 2026.
Maintaining that type of growth will be critical if the company is to reach a $1 trillion market cap within five years. Sandisk also boasts a surging net profit margin, which exceeded 60% in the most recent quarter. It was just 26.6% in the previous quarter, and in the one prior to that, it was just 4.9%.
Micron surprised many investors by reaching a $1 trillion market cap shortly after unlocking the perks of AI memory demand. Sandisk is achieving a similar degree of fundamental growth, but still is generating only about one-fourth of the revenue of Micron.
One of the main concerns about investing in memory companies is that they operate in a cyclical industry. At intervals, demand grows for their products, resulting in a boom and a shortage, at which point the various players begin the multiyear process of building new production facilities to capitalize. In each previous cycle, supply has caught up to and exceeded waning demand, and those memory makers were left with inventory gluts that compelled them to cut prices and lower their margins.
The bust part of this boom-and-bust cycle seems far away, though, and elevated demand for memory chips may become the new normal. Nvidia CEO Jensen Huang anticipates more than $1 trillion in data center revenue for his company across 2026 and 2027. That means there will be plenty of demand for memory chips, which are critical hardware for AI infrastructure.
This also comes at a time when tech companies are ramping up their AI spending and seeing tangible results from those investments. As new innovations such as self-driving cars or agentic AI go mainstream, they will further boost demand for AI and memory chips, which will benefit Sandisk.
The company has already sold all the NAND flash drives it will be able to manufacture in 2026 and is generating strong demand for its 2027 production. Furthermore, in a recent report, Melius Research predicted that memory demand will remain strong through the end of the decade. Based on that outlook, Sandisk has a real shot at becoming a $1 trillion company within five years.
Before you buy stock in Sandisk, 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 Sandisk 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 30, 2026. *
Marc Guberti has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Micron Technology, Nvidia, and Western Digital. 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.
Bốn mô hình AI hàng đầu thảo luận bài viết này
"Memory's cyclical supply response will likely cap Sandisk's margins and valuation well below $1 trillion within five years."
The article pushes Sandisk (SNDK) toward a $1T valuation on AI memory demand, sold-out 2026 capacity, and Melius' decade-long forecast. Yet it downplays the sector's boom-bust pattern: every prior shortage triggered multi-year fab builds that flooded supply and collapsed prices. Sandisk's post-spin revenue of $5.95B with 60% margins in FQ3'26 is impressive but far below Micron's scale, and those margins likely compress once new capacity arrives. Nvidia's data center spend helps, but doesn't guarantee structural pricing power against Samsung and SK Hynix expansions.
Even if historical cycles repeat, unprecedented AI-driven demand could keep utilization high enough to sustain elevated pricing through 2030, validating the re-rating.
"A multiyear shortage does not equal a multiyear margin expansion; the moment supply normalizes, Sandisk faces the same cyclical compression that has plagued memory makers for decades, making $1T valuation dependent on a structural demand shift the article asserts but doesn't prove."
The article conflates two separate phenomena: a genuine near-term supply crunch (2026–2027 sold out) with a structural demand thesis. The 4,200% return and 60%+ net margins are classic late-cycle signals, not proof of durability. Sandisk's revenue is $5.95B annualized (~$24B run rate); reaching $1T valuation requires either 40x revenue multiple or 40x earnings multiple—both unsustainable if supply catches up. The Melius forecast of 'strong demand through decade's end' is vague and doesn't account for capex cycles by competitors or margin compression. Micron's $1T valuation is itself questionable at current multiples.
If AI infrastructure truly becomes a permanent capex category (not a cycle) and Sandisk locks in long-term contracts at premium pricing while competitors struggle with fab buildout, the company could sustain elevated margins longer than historical cycles suggest—especially if geopolitical constraints limit supply.
"The current 60% net profit margin is a cyclical anomaly that will inevitably revert as production capacity catches up to demand, making a $1 trillion valuation target fundamentally unrealistic."
The article’s premise that SanDisk (SNDK) can reach a $1 trillion valuation is mathematically aggressive and ignores the inherent volatility of the NAND flash market. While the 60% net profit margin is impressive, it is likely a cyclical peak rather than a sustainable structural baseline. The comparison to Micron (MU) is fraught; Micron is a diversified DRAM and NAND powerhouse, whereas SanDisk’s reliance on NAND exposes it to extreme price sensitivity and commodity-like competition. Investors should be wary of extrapolating current 'sold-out' status into a permanent state of pricing power. Without a broader product moat, SanDisk remains a high-beta play on data center capital expenditure, not a secular compounder.
If AI-driven data center demand truly creates a 'super-cycle' where supply cannot catch up for years, SanDisk’s current margins could compress less than historical cycles, justifying a higher valuation multiple.
"SNDK could justify a trillion-dollar market cap if durable AI-memory demand sustains high margins and Sandisk scales capacity enough to unlock meaningful free cash flow."
The piece paints a bullish case for Sandisk (SNDK) on AI-driven memory demand and a sell-out for 2027, implying a path to a $1T market cap. Yet memory cycles are inherently volatile; sustained margins at 60% are unusual and may reflect one-offs or mix effects. Sandisk’s revenue is still a fraction of Micron’s, so outsized capex to expand NAND could pressure returns unless pricing remains firm. The claim of a multi-year supply shortage glosses over potential rapid capacity additions and price erosion. A valuation hinge on multiple expansion and a structural shift in memory pricing, not just growth, remains a big assumption.
Even if AI demand stays hot, Sandisk would need durable margins and massive FCF to justify a $1T tag; cyclicality and competitive supply could snap the rug out from under this thesis, limiting multiple expansion.
"Contract timing before competitor ramps could sustain elevated margins longer than cycle history predicts."
Claude's valuation math treats the $24B run rate as fixed, yet ignores how sold-out 2026-27 capacity lets Sandisk sign multi-year AI contracts at fixed premiums before Samsung and SK Hynix fabs ramp. That sequencing could preserve 45%+ margins into 2028 even if overall supply later rises, decoupling Sandisk's earnings trajectory from the classic boom-bust pattern the rest of the panel assumes will repeat unchanged.
"Contract lock-in buys time but doesn't eliminate the structural risk that competitors' capex cycles will eventually overwhelm Sandisk's temporary supply advantage."
Grok's multi-year contract lock-in thesis is plausible but unverified by the article. The risk: even if Sandisk signs premium deals through 2028, Samsung and SK Hynix have massive balance sheets and geopolitical backing to accelerate capex regardless. Contracts don't prevent spot-market price collapse if competitors flood supply. The sequencing advantage assumes competitors *can't* or *won't* match capacity timing—a dangerous assumption in a $500B+ industry.
"SanDisk's valuation is tethered to HBM capability, not just NAND capacity, making the $1T target fundamentally misaligned with their current product mix."
Claude and Grok are debating contract lock-ins, but both miss the crucial technological shift: HBM (High Bandwidth Memory) is the real catalyst, not generic NAND. SanDisk’s valuation hinges on whether they can pivot from commodity storage to high-margin, AI-specific compute memory. If they remain tethered to NAND, they are a commodity player regardless of contract duration. The $1T valuation is pure fantasy unless they dominate the HBM supply chain, which currently belongs to SK Hynix and Micron.
"HBM alone won't secure durable, high-margin growth for Sandisk; capex cycles and commodity-like NAND price dynamics will erode any 'supercycle' unless Sandisk proves a true moat."
Gemini overemphasizes HBM as the sole catalyst. Even if HBM demand materializes, Sandisk's moat for AI-specific memory is unproven; HBM supply is concentrated with a few players, and Sandisk would need durable contracts and design wins to sustain 60%+ margins. If NAND supply expands and HBM capacity ramps, pricing power will compress. The real risk is a bifurcated cycle: AI demand may not translate into lasting margin resilience across multiple product lines.
The panel largely agrees that Sandisk's current high margins and valuation are unsustainable due to the volatile nature of the memory market and potential supply increases from competitors. However, there's debate on whether Sandisk can maintain pricing power through long-term contracts or by pivoting to high-margin AI-specific memory.
Potential for Sandisk to maintain high margins through long-term contracts or by successfully pivoting to high-margin AI-specific memory.
Potential supply increases from competitors like Samsung and SK Hynix, which could flood the market and collapse prices.