By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel consensus is bearish on Sandisk (SNDK) and Western Digital (WDC), citing cyclical NAND dynamics, potential overbuild, and intense competition from Samsung and SK Hynix. They agree that the current rally is unsustainable and likely to reverse, with margins compressing once supply catches up to demand.
Risk: Flooding of supply within 18-24 months by competitors, leading to margin compression before WDC can capture sustained pricing power or reduce its debt.
Opportunity: None identified by the panel.
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 →
Sandisk is thriving due to a severe memory chip shortage.
The memory chip crunch could last for years as data center build-outs ramp up.
Few stocks have delivered as compelling a performance over the past year or so as Sandisk (NASDAQ: SNDK). The memory specialist has delivered monster returns for investors who picked up shares shortly after its spinoff from Western Digital, which bought it in 2016.
If you had the foresight to invest $30,000 during the spinoff (which occurred on Feb. 24, 2025) and held on through the astonishing run that followed, the value of your stake would now be more than $1 million. That's an incredible gain in just over a year's time.
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 »
But for those investors who haven't already gotten into the stock, the question is, can Sandisk's run continue, or has it reached its peak?
Sandisk makes NAND memory, which is primarily utilized for long-term data storage. Its products are mostly used to make solid-state drives (SSDs), which are used in data centers to house data and information. Sandisk and its peers don't have the production capacity to make enough NAND for SSDs to meet soaring data center demand. As a result, prices for these commodity components have soared, and Sandisk's revenues and profits have skyrocketed.
Sandisk is currently in the fourth quarter of its fiscal 2026. For this period, Wall Street analysts expect 332% year-over-year revenue growth. For fiscal 2027, Wall Street analysts expect 118% growth. That demonstrates how much the prices of memory are soaring, and the shortage driving those price hikes could last for a long time as data center spending continues to ramp up.
A great source of insight about the future pace of data center expansion is Nvidia (NASDAQ: NVDA). The world's largest company has its fingers on the AI build-out pulse, and is a close partner with every AI company. Those relationships are helping it plan to meet demand for its AI accelerators down the road. While the big four AI hyperscalers say they plan to lay out about $650 billion in data center capital expenditures during 2026, Nvidia told investors that their collective capex will top $1 trillion in 2027. Furthermore, by 2030, it expects global annual data center capital expenditures to reach $3 trillion to $4 trillion.
Those new data centers will need more than just an enormous quantity of AI accelerators -- they'll also need a ton of memory, which bodes well for the long-term outlook of Sandisk. In that context, investors shouldn't view it as some flash-in-the-pan company that rises massively one year, then plunges the next. Its business will have a ton of staying power as long as the AI data center build-out is ongoing and as long as the production capacity of memory-chip makers lags behind demand. Once the AI build-out slows, Sandisk's stock may fare poorly, but it could be many years before that happens. As a result, Sandisk's stock could still be a smart AI investment.
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 $439,038! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,277,804!
Now, it’s worth noting Stock Advisor’s total average return is 942% — a market-crushing outperformance compared to 206% 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 10, 2026. *
Keithen Drury has positions in Nvidia. The Motley Fool has positions in and recommends 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.
Four leading AI models discuss this article
"Sandisk's post-spinoff surge hinges on a persistent NAND shortage and AI-led capex; but a memory-price normalization or quicker supply response could erode the thesis and trigger meaningful downside."
Despite the article's bullish tone, the Sandisk rally rests on a cyclical NAND dynamic—memory prices and data-center demand. A year of gains can be erased by a memory-price normalization, faster-than-expected capacity additions, or slower AI capex than forecast. The piece cites Nvidia and 2027 capex to justify a long runway, but it lacks detail on Sandisk's pricing power, margins, and mix. The spinoff narrative may amplify enthusiasm without proving durable earnings. If supply ramps faster or demand softens, Sandisk could see multiple compression even as AI spending remains uncertain.
Even if AI demand persists, the rally may reverse: NAND price cycles revert and capacity catches up, squeezing margins. Absent sustained pricing power or a favorable mix, gains could fade.
"The explosive revenue growth cited is a cyclical peak in a commodity market that historically leads to over-capacity and margin compression, making the current valuation unsustainable."
The article's narrative on Sandisk (SNDK) is a classic 'rearview mirror' trap. While the 332% revenue growth figure is eye-catching, it reflects a cyclical peak in NAND pricing, not a permanent structural shift. Memory is a notoriously commoditized, capital-intensive industry prone to 'boom-bust' cycles. By the time retail investors read about 'monster returns' and 'shortages,' the supply-side response—new fab capacity—is usually already in motion. Betting on Sandisk here assumes the current pricing power holds through a massive capex cycle, ignoring the historical tendency for memory makers to overbuild and crash margins once supply finally catches up to demand.
If the AI data center build-out truly hits the $3 trillion annual capex mark by 2030, the resulting demand for high-density storage could create a supply deficit so structural that historical cyclicality becomes irrelevant.
"Sandisk is a cyclical commodity play masquerading as a structural AI beneficiary; current valuations price in permanent shortage economics that will evaporate within 18-24 months as foundry capacity comes online."
The article conflates two separate dynamics: a cyclical commodity super-cycle (memory prices spiking due to supply lag) with a structural secular trend (AI capex durability). The math is seductive—332% YoY revenue growth in Q4 FY2026—but this is peak-cycle pricing, not normalized demand. Sandisk's margins will compress viciously once capacity catches up, which TSMC and Samsung are already racing to do. The article also ignores that hyperscalers are vertically integrating memory production (see: Google, Meta custom chips). The $1M return narrative is survivorship bias dressed as foresight. What matters now is whether SNDK can maintain 40%+ gross margins post-shortage.
If AI capex truly scales to $3-4T annually by 2030 as Nvidia projects, memory demand could outpace supply for 5+ years, sustaining pricing power and making current valuations rational rather than speculative.
"SanDisk has not existed as a public company since 2016, making the article's $30k-to-$1M spinoff scenario factually impossible."
The article's core premise collapses on basic facts: SanDisk was fully acquired by Western Digital in 2016 and delisted, so no public spinoff occurred on Feb. 24, 2025, and SNDK shares have not traded since. Projected 332% revenue growth in fiscal Q4 2026 and trillion-dollar data-center capex tailwinds may describe NAND dynamics broadly, but cannot apply to a nonexistent standalone entity. Investors chasing the claimed million-dollar outcome from a $30k spinoff purchase face an impossible timeline and nonexistent security. Any real exposure would route through Western Digital (WDC), whose NAND margins remain volatile and capacity-constrained by competitors like Samsung and SK Hynix.
The article could be using 'Sandisk' loosely as shorthand for WDC's flash business, in which case the multi-year AI-driven NAND shortage thesis would still hold even if the ticker and spinoff details are sloppy.
"The Sandisk spinoff premise is misframed; exposure sits with WDC, and the bull case hinges on a long-lasting, non-cyclical NAND pricing power that current cyclicality challenges."
Grok, your take rests on a Sandisk spin-off that never happened; SNDK isn’t a live independent ticker, so the $30k to $1M payout via a spinoff is misframed. Real exposure is through Western Digital (WDC), whose NAND margins are cyclical. If capex-driven demand fades or overbuild materializes, the narrative risks a re-rating away and leaves little durable upside beyond a fleeting cycle.
"WDC's debt profile is a more significant risk to shareholder value than the cyclicality of NAND pricing."
Grok, your correction on the ticker is vital, but let's address the WDC exposure directly. If investors are chasing this 'spinoff' narrative, they are likely ignoring the massive debt load WDC carries from the original acquisition. Even if the AI NAND thesis holds, WDC’s balance sheet is the real bottleneck. It’s not just a cyclical memory play; it’s a deleveraging story. If they can’t pay down debt during this cycle, the equity remains effectively trapped.
"WDC's bottleneck isn't debt service—it's the capex-timing trap between under-investing (losing share) and over-investing (stranded assets)."
Gemini's debt angle is underexplored but incomplete. WDC's net debt (~$5.8B) is material, yet the real constraint isn't deleveraging capacity—it's capex intensity. During a NAND shortage, WDC must choose: pay down debt or fund fab expansion to capture pricing power. If they under-invest, competitors gain share; if they over-invest, they're left stranded when the cycle turns. The debt doesn't trap equity; the capex dilemma does. That's the actual binary.
"Competitor capacity expansions will compress margins before WDC can address its debt or capex needs effectively."
Claude flags WDC's capex dilemma versus debt reduction, yet the larger issue is competitor capacity: Samsung and SK Hynix are expanding fabs aggressively. This will flood supply within 18-24 months, compressing NAND margins before WDC captures sustained pricing power or reduces its $5.8B net debt meaningfully. The binary isn't investment choice alone—it's whether WDC can outpace rivals in a commoditized market where overbuild is endemic.
The panel consensus is bearish on Sandisk (SNDK) and Western Digital (WDC), citing cyclical NAND dynamics, potential overbuild, and intense competition from Samsung and SK Hynix. They agree that the current rally is unsustainable and likely to reverse, with margins compressing once supply catches up to demand.
None identified by the panel.
Flooding of supply within 18-24 months by competitors, leading to margin compression before WDC can capture sustained pricing power or reduce its debt.