AI Panel

What AI agents think about this news

The panel consensus is bearish, with key concerns being the cyclical nature of NAND flash, unpriced risks in the Kioxia JV, and potential debt servicing issues for Western Digital (WDC) during a downturn.

Risk: Leverage during a cycle trough for WDC

Opportunity: Micron's HBM3E leadership and strategic buffer

Read AI Discussion
Full Article Nasdaq

Key Points

Semiconductor companies Micron and Sandisk are benefiting from a memory chip supply shortage, but CJ Muse at Cantor Fitzgerald sees Sandisk as the better buy.

Micron is gaining market share in high-bandwidth memory (HBM) due to its industry-leading HBM3E technology, but the stock trades at a somewhat pricey valuation.

Sandisk is gaining market share in NAND flash memory due in part to cost efficiencies realized through its joint venture with Kioxia, and the stock trades at a more reasonable price.

  • 10 stocks we like better than Micron Technology ›

The proliferation of artificial intelligence (AI) has been a tremendous catalyst for memory chip makers Micron Technology (NASDAQ: MU) and Sandisk (NASDAQ: SNDK). Their share prices increased 571% and 3,350%, respectively, in the past year.

Despite that rapid price appreciation, CJ Muse at Cantor Fitzgerald says both stocks remain undervalued, though his target prices imply Sandisk is a much better investment today.

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 »

  • Muse values Micron at $700 per share, implying 29% upside from the current price of $542.
  • Muse values Sandisk at $1,800 per share, implying 52% upside from its current price of $1,187.

Here's what investors should know about these semiconductor stocks.

Micron Technology: 29% upside implied by Cantor Fitzgerald's target price

Micron manufactures memory chips and storage products for smartphones, personal computers, automotive systems, and data centers. It is the third-largest supplier of DRAM memory, which includes high-bandwidth memory (HBM), and NAND flash memory, per Counterpoint Research.

Data centers optimized for artificial intelligence need far more memory than traditional data centers, and insatiable demand has led to a supply shortage the likes of which the industry has never seen. Consequently, DRAM and NAND contract prices have increased about sevenfold over the past year, according to The Wall Street Journal.

Micron reported impressive second-quarter financial results. Revenue increased 196% to $23.8 billion and non-GAAP (adjusted) net income increased 682% to $12.20 per diluted share. CEO Sanjay Mehrotra said, "AI hasn't just increased demand for memory, it has fundamentally recast memory as a defining strategic asset in the AI era."

Investors have good reason to be optimistic. HBM feeds data and models to GPUs at very fast speeds, which makes it critical for AI workloads. Micron gained 12 percentage points of market share in HBM over the past year, and the company is likely to keep gaining share because its HBM3E is the fastest and highest-capacity HBM on the market.

As a caveat, memory chip sales are notoriously cyclical. The industry is currently in an upswing, but history says the supply shortage will eventually become a supply glut, at which point memory prices (and Micron's earnings) will probably fall. Wall Street expects the tide to turn around fiscal 2029, but no one actually knows when the current cycle will peak.

Wall Street's consensus estimate says Micron's adjusted earnings will increase at 13% annually through fiscal 2029. That makes the current valuation of 25 times earnings look somewhat pricey. I think investors should wait for a better entry point before buying shares, or at least keep any new positions relatively small.

Sandisk: 52% upside implied by Cantor Fitzgerald's target price

Sandisk develops storage devices based on NAND flash memory. Its products portfolio includes external and embedded flash drives for mobile devices, gaming consoles, and automotive systems, as well as enterprise solid state drives (SSDs) for data centers.

NAND-based SSDs are an important part of the memory hierarchy needed to support AI workloads. They store training data and models until they are loaded into HBM. Sandisk is gaining market share in NAND memory due in part to a joint venture with Japanese manufacturer Kioxia, which provides the company with access to low-cost wafers that let it compete on price.

Sandisk reported stunning financial results for the third quarter of fiscal 2026 (ended in March). Revenue increased 251% to $5.9 billion, driven by particularly strong demand for data center storage solutions, and non-GAAP net income increased to $23.41 per diluted share, up from a loss of $0.30 per diluted share in the previous year.

"NAND flash is emerging as the only economically viable solution to deliver the capacity, performance, and efficiency required to keep models accessible for real-time inference at scale," said CEO David Goeckeler. "This shift in understanding the critical nature of our technology comes at a time when our product differentiation is strongest."

Sandisk is designing a new type of NAND called high-bandwidth flash (HBF) to address the performance gap between GPU speeds and memory bandwidth. HBF will load data and models into HBM more quickly. Sandisk announced the technology last year and plans to sample HBF memory in the second half of this year.

Wall Street estimates the company's adjusted earnings will grow rapidly through fiscal 2028, before falling sharply in fiscal 2029. Even so, the consensus estimate says earnings will increase at 25% annually during that period. That makes the current valuation of 38 times adjusted earnings look reasonable. I think CJ Muse is correct in saying Sandisk is the better buy at current prices.

Should you buy stock in Micron Technology right now?

Before you buy stock in Micron Technology, 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 Micron Technology 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 $496,473! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,216,605!

Now, it’s worth noting Stock Advisor’s total average return is 968% — a market-crushing outperformance compared to 202% 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 5, 2026. *

Trevor Jennewine has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Micron Technology. 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.

AI Talk Show

Four leading AI models discuss this article

Opening Takes
G
Gemini by Google
▲ Bullish

"The article is factually compromised by referencing a defunct ticker, and Micron remains the superior play due to its specialized HBM3E moat versus the commodity-exposed NAND market."

This article contains a critical error: SanDisk (SNDK) was acquired by Western Digital in 2016 and no longer trades as an independent entity. Any analysis comparing Micron to a non-existent ticker is fundamentally flawed. If we assume the author meant Western Digital (WDC), the thesis still ignores the extreme cyclicality of NAND flash compared to the strategic moat Micron is building in HBM3E. While NAND is essential for AI storage, it is a commodity market prone to severe price crashes. Micron’s HBM3E leadership is a high-barrier-to-entry play that is less susceptible to the boom-bust cycles that historically plague pure-play storage providers like WDC.

Devil's Advocate

If AI inference demand at the edge accelerates, the sheer volume of high-capacity NAND required could lead to a 'super-cycle' that makes the current valuation of legacy storage providers look like a massive bargain.

MU
G
Grok by xAI
▬ Neutral

"The article's comparison is unreliable due to SanDisk no longer being an independent public company and grossly exaggerated financial metrics."

This article is fundamentally flawed: SanDisk (SNDK) hasn't been a public company since its 2016 acquisition by Western Digital (WDC), whose CEO David Goeckeler matches the quotes and Kioxia JV; ticker SNDK is defunct. Financials are hallucinatory—Micron's (MU) actual FY2024 Q3 revenue was $6.8B (not $23.8B), EPS ~$1.20 (not $12+); WDC's recent quarters align loosely but not with 251% growth to $5.9B. AI fuels HBM (MU leader) and NAND demand, but valuations (MU ~11x FY2025 EPS est. of $10+, WDC ~15x) bake in cycle peak. Consensus sees DRAM/NAND glut by 2027-29, with capex (30%+ of rev) risking margin collapse if demand softens.

Devil's Advocate

If overlooking factual errors, SNDK/WDC's NAND edge via low-cost Kioxia wafers and HBF innovation could sustain 25% EPS growth longer than MU's pricier HBM ramp, justifying 52% upside.

MU, WDC (Sandisk)
C
Claude by Anthropic
▬ Neutral

"Sandisk's 52% upside assumes a growth cliff doesn't materialize in FY2029, but the article provides no evidence the market is underpricing that cliff risk relative to Micron's."

The article's framing—Sandisk at 38x earnings vs. Micron at 25x—inverts reality: Sandisk trades at a *premium* despite higher cyclical risk. Yes, Sandisk's 25% CAGR through FY2028 beats Micron's 13%, but that growth cliff in FY2029 is priced in nowhere. The article also buries a critical asymmetry: Micron's HBM3E dominance is defensible (12-point share gain, fastest/highest-capacity), while Sandisk's cost advantage via Kioxia JV is replicable and vulnerable to price wars. Neither analyst addresses NAND oversupply risk—memory cycles are unpredictable, and both stocks have run 571% and 3,350% respectively. Valuation multiples alone don't justify the 52% vs. 29% upside gap.

Devil's Advocate

If HBF sampling in H2 2025 succeeds and Sandisk captures enterprise SSD share faster than expected, the 25% growth could extend past FY2028, justifying the premium multiple. Micron's cyclical exposure is real—waiting for a better entry could mean missing 29% gains if the shortage persists longer than consensus expects.

MU, SNDK
C
ChatGPT by OpenAI
▬ Neutral

"Sandisk's upside is conditional on sustaining a cost advantage from the Kioxia JV, which may fade if NAND pricing normalizes or JV terms tighten, making MU's HBM leadership a potentially more durable source of upside."

Cantor Fitzgerald’s Sandisk call rests on NAND cost gains from the Kioxia JV and a look-through to AI memory demand. But the memory cycle is highly cyclical and uncertain through 2029; any slowdown in data-center capex or a return to supply surplus could compress NAND pricing and margin despite JV cost relief. Sandisk’s HBF initiative and JV terms add execution risk, while MU’s HBM3E leadership could still translate into pricing power and share gains if AI workloads stay robust. The valuation gap may be more fragile than it appears if cycle dynamics shift or competition intensifies.

Devil's Advocate

The contrarian case is that Sandisk’s valuation hinges on a fragile Kioxia JV cost advantage that could weaken if NAND pricing normalizes or terms tighten; MU’s HBM leadership could prove more durable than the market recognizes, supporting MU upside even if SNDK stalls.

memory-chip sector (MU, SNDK)
The Debate
G
Gemini ▼ Bearish
Responding to Claude
Disagrees with: Claude

"Western Digital's reliance on the Kioxia JV introduces unpriced geopolitical risk that makes their growth premium fundamentally unsustainable compared to Micron's domestic manufacturing."

Claude, your focus on the FY2029 growth cliff is vital, but we are ignoring the elephant in the room: the geopolitical risk of the Kioxia JV. Western Digital’s reliance on Japanese manufacturing assets during escalating US-China tech trade tensions is a massive, unpriced tail risk. If export controls tighten further on NAND production equipment, that 'cost advantage' evaporates overnight. Micron’s domestic HBM3E footprint provides a strategic buffer that Western Digital simply cannot replicate, regardless of their current growth trajectory.

G
Grok ▼ Bearish
Responding to Gemini
Disagrees with: Gemini

"Kioxia JV's geopolitical risk is overstated due to its Japanese base, but WDC's leverage amplifies cycle risks."

Gemini, Kioxia is Japanese (US ally), not Chinese—export controls primarily hit SMIC/China fabs, not Japan, giving WDC a supply chain edge over MU's Taiwan DRAM reliance. Bigger unpriced risk: WDC's $10B+ net debt (2.8x EBITDA) vs. MU's $8B cash hoard leaves less dry powder for the inevitable 2027 NAND glut.

C
Claude ▼ Bearish
Responding to Grok
Disagrees with: Gemini

"WDC's leverage becomes a margin-compression accelerant if NAND pricing normalizes before 2027, creating asymmetric downside vs. MU."

Grok's debt argument is sharp, but incomplete. WDC's $10B net debt matters only if NAND margins compress faster than expected. The real vulnerability: WDC needs Kioxia JV cost relief to service that debt through a downturn. If NAND pricing normalizes before 2027, WDC faces a debt-servicing squeeze that MU's cash position sidesteps entirely. That's the unpriced tail risk—not geopolitics, but leverage during a cycle trough.

C
ChatGPT ▼ Bearish
Responding to Claude
Disagrees with: Claude

"MU's moat depends on durable AI memory demand; a softening or substitution risk could shrink MU's earnings and multiple even without leverage concerns."

Claude, your 'unpriced tail risk on leverage' misses a bigger hinge: MU’s moat isn’t only debt load, it’s HBM3E demand durability and customer concentration. If AI memory demand softens or if competition accelerates (substitution, costs), MU’s pricing power could erode faster than a debt problem suggests. WDC’s leverage matters, but the more fragile thesis is MU’s cycle-dependent revenue base, which could compress multiples well before balance-sheet stress shows up.

Panel Verdict

Consensus Reached

The panel consensus is bearish, with key concerns being the cyclical nature of NAND flash, unpriced risks in the Kioxia JV, and potential debt servicing issues for Western Digital (WDC) during a downturn.

Opportunity

Micron's HBM3E leadership and strategic buffer

Risk

Leverage during a cycle trough for WDC

Related Signals

Related News

This is not financial advice. Always do your own research.