By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel consensus is bearish, with the key risk being a potential collapse in gross margins due to faster-than-expected capacity increases from competitors or aggressive price negotiations by major customers.
Risk: Faster-than-expected capacity increases from competitors or aggressive price negotiations by major customers leading to a collapse in gross margins.
Opportunity: None identified
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 →
Few stocks have ridden the artificial intelligence (AI) boom quite like Micron Technology (NASDAQ: MU). The memory chipmaker's stock has more than tripled in 2026, up nearly 300% year to date as of this writing and trading around $1,134 after a fresh run to record highs. The company is now valued at close to $1.3 trillion.
That sets a high bar heading into Wednesday. When Micron reports its fiscal third quarter of 2026 (the period ended May 28, 2026) after the close on June 24, another set of records looks all but assured -- management guided months ago for staggering growth. The real question is whether the outlook that comes with the report can justify a stock price that already assumes the boom keeps going.
Where to invest $1,000 right now? Our analyst team just revealed what they believe are the 10 best stocks to buy right now, when you join Stock Advisor. See the stocks »
The headline figure will be revenue. Micron has guided for about $33.5 billion, give or take $750 million -- up about 40% from the $23.86 billion it reported in its fiscal second quarter, which had itself nearly tripled from a year earlier. To put that in perspective, management has noted that its fiscal third-quarter revenue guidance alone tops the company's total revenue for any full year through fiscal 2024.
Management also guided for a record non-GAAP (adjusted) gross margin of about 81% and earnings per share of around $19.15.
But the records aren't really the question -- the company's guidance all but assures them -- or at least something in the ballpark of what management guided for. What matters is what management says about memory pricing and supply.
That commentary is the engine behind the entire run. Micron has completed agreements on price and volume for its entire calendar 2026 high-bandwidth memory (HBM) supply.
"We expect both DRAM and NAND industry bit demand in calendar 2026 to be constrained by supply," Micron said in its fiscal second-quarter prepared remarks, adding that it expects conditions to stay tight beyond this year.
The shortage, of course, traces back to AI.
Each new generation of Nvidia (NASDAQ: NVDA) chip -- the graphics processing units (GPUs) at the center of AI computing -- needs more memory, and the most advanced type uses far more factory capacity per bit than ordinary memory does. So as Micron shifts production toward HBM for Nvidia's next-generation Vera Rubin platform, it pulls capacity away from the standard memory that goes into laptops and data-center servers, keeping prices elevated.
Memory is a famously cyclical business, and every prior boom has eventually given way to a glut of supply and falling prices. So, the most telling part of this report may not be the May quarter at all, but what management signals about 2027.
What would be a red flag for investors? Any hint that pricing can't keep pushing higher would likely worry investors. Pricing, of course, is determined by supply and demand. And Micron has completed its 2026 HBM capacity supply agreements. But management is still working with customers on strategic customer agreements with specific multi-year commitments, and any softening there could signal that supply is starting to catch up with demand. And investors will be watching margins, too. Achieving its adjusted gross margin guidance of about 81% would already mark a record. But it's worth watching whether management expects that level to hold or to flatten from here.
For now, the supply side still looks tight. Micron and its rivals are spending tens of billions on new factories -- including plants going up in Idaho and New York, with the first Idaho fab expected to begin initial wafer output in mid-calendar 2027 and the first New York fab expected to provide supply in 2030 and beyond. But those capital expenditures won't add meaningful capacity until late 2027. That could keep the squeeze in place a while longer.
And that is the heart of the valuation debate. At around $1,134, Micron trades at more than 50 times earnings -- a multiple that looks steep for a memory maker. But those trailing earnings barely capture the inflection underway. The company's guidance for about $19.15 in fiscal third-quarter earnings per share alone sits well above the $12.20 it earned in the quarter just reported, so the stock looks far cheaper measured against what it could earn over the next year -- assuming the cycle holds.
So is the rally finished?
I don't think this quarter will settle it. The records are essentially baked in, and for me, the report comes down to the outlook. As long as management keeps describing a market short on supply and signals that 2027 is shaping up much like 2026, the bull case will likely remain intact.
But the price now leaves little room for disappointment. A cautious word on next year's pricing, or any sign that customers are pulling back, could knock the stock down hard, given how much optimism is already priced in. The memory boom may well keep running. The risk, after a year like this one, is that the market is counting on it.
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 $415,040! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,256,076!
Now, it’s worth noting Stock Advisor’s total average return is 920% — 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 June 19, 2026. *
Daniel Sparks and his clients have no position in any of the stocks mentioned. The Motley Fool has positions in and recommends 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
"MU's upside relies on sustained AI-driven memory demand and tight pricing into 2027; any early signs of easing demand or faster capacity ramp could trigger a sharp re-rating."
Micron's guide for roughly $33.5B revenue and an ~81% gross margin anchors a bullish view that AI-driven memory demand will stay tight into 2027. The stock trades rich, but the thesis hinges on supply remaining constrained as new fabs come online—HBM-focused capacity matters for Nvidia's Vera Rubin, and 2027-2030 ramps could extend the cycle. However, the article downplays cyclical risk: memory historically overextends, pricing can roll over once capacity catches up, and 2027 capex timing could shift supply sooner than expected. Any sign of easing demand or faster-than-anticipated capacity could compress margins and multiples.
Against my stance: The cycle could turn earlier if AI demand softens or if new fabs push supply faster than expected; the >50x earnings multiple leaves little room for error.
"Micron's current valuation assumes a permanent departure from cyclicality that the underlying capital expenditure cycle and historical commodity dynamics do not support."
Micron’s valuation at a $1.3 trillion market cap is pricing in perfection, effectively treating a historically cyclical commodity business like a secular software-as-a-service play. While the HBM supply constraint is real, the market is ignoring the 'bullwhip effect' risk: as Micron and its competitors aggressively deploy massive CapEx for Idaho and New York fabs, the eventual supply glut in 2027-2028 could be catastrophic for margins. An 81% gross margin is unsustainable in a commodity-linked industry. If management signals any shift in multi-year pricing agreements or if HBM yield improvements outpace customer demand, the forward P/E multiple will face a violent contraction.
If AI inference demand scales exponentially, the HBM supply deficit may persist well into 2028, allowing Micron to maintain pricing power far longer than historical cycles would suggest.
"MU's valuation requires not just supply scarcity but also pricing discipline across HBM, DRAM, and NAND through 2027—a three-variable bet where historical precedent suggests at least one fails."
MU at 50x forward earnings is pricing in perfect execution of a multi-year supply constraint that doesn't exist in isolation. Yes, HBM demand is real and capacity-constrained through 2026—that's baked in. But the article glosses over a critical vulnerability: Micron's 81% gross margin guidance assumes HBM pricing holds while DRAM/NAND remain elevated. If even one major customer (hyperscaler) negotiates aggressively on 2027 volumes—or if competing HBM suppliers (SK Hynix, Samsung) ramp faster than expected—margin compression could be severe. The stock has tripled on a thesis that requires both supply scarcity AND pricing discipline to persist 18+ months. History suggests memory cycles break faster than investors expect.
If management reaffirms tight 2027 supply and signals $20+ EPS is achievable, the stock could re-rate higher on a lower multiple as the cycle extends—memory booms have surprised to the upside before, and AI demand may be genuinely different this time.
"The memory supply crunch is likely to ease earlier than 2027 as competitors scale HBM production, pressuring Micron's margins and valuation."
Micron's guided $33.5B Q3 revenue and 81% gross margins reflect AI tailwinds, but the stock's 50x trailing earnings and $1.3T valuation embed perfection through 2027. The piece highlights delayed new capacity from Idaho and New York fabs, yet overlooks that SK Hynix and Samsung are also ramping HBM aggressively with potentially earlier yields. Any acceleration in competitor supply or a pause in Nvidia's next-gen orders would expose the cyclical downside faster than expected. Management's 2027 commentary will be pivotal, but current pricing leaves scant room for supply normalization signals.
Micron has already locked in all 2026 HBM volumes at premium prices, and its technology lead in HBM3E could sustain 70%+ margins even if rivals add capacity, supporting further multiple expansion if EPS hits $70+ annualized.
"Margin resilience depends more on pricing leverage and yield dynamics than on capex-driven supply constraints."
Gemini overplays a near-term mega-capacity glut; the real shock could be timing risk: if HBM yields improve or hyperscalers renegotiate 2027 volumes, gross margins collapse faster than the stock implies. The panel underweights DRAM/NAND pricing leverage and take-or-pay contracts that could constrain Micron’s ability to sustain 80%+ GM into 2027, even with capex running. The bull case needs harder guardrails on pricing discipline and yield curves.
"Projecting $70 EPS ignores the fundamental reality of high depreciation costs and the cyclical nature of the broader memory business."
Grok, your $70+ EPS projection is pure fantasy. Even with HBM dominance, Micron’s historical peak net margins rarely exceed 30%. Expecting $70 EPS implies a structural shift from a cyclical hardware manufacturer to a high-margin software monopoly that simply isn't supported by the underlying DRAM/NAND business. You are ignoring the massive depreciation drag from the new Idaho/New York fabs, which will weigh heavily on GAAP earnings regardless of how tight the HBM supply remains.
"Micron's bull case hinges on HBM sustaining 81% GM while NAND/DRAM don't compress—a two-variable dependency the market isn't stress-testing."
Gemini's $70 EPS critique is valid on historical margins, but misses Micron's actual 2025-2026 guidance trajectory. Management projects $20-22 EPS annualized by late 2025—that's not fantasy, it's disclosed. The depreciation drag is real, but Gemini conflates GAAP with operating leverage. The harder question: does HBM's 81% GM offset NAND/DRAM compression? If NAND pricing rolls in 2026, even tight HBM supply can't hold blended margins above 65%. That's the margin cliff nobody's quantifying.
"NAND weakness plus take-or-pay flexibility could cap EPS well below guidance even before capacity normalizes."
Gemini rightly calls out depreciation drag from new fabs, yet the bigger unaddressed risk is Claude's NAND pricing rollover in 2026 eroding blended margins below 65% even with locked HBM volumes. If hyperscalers push back on take-or-pay terms amid softening AI capex, the $20-22 EPS trajectory breaks before any 2027 supply glut materializes, compressing multiples faster than historical cycles.
The panel consensus is bearish, with the key risk being a potential collapse in gross margins due to faster-than-expected capacity increases from competitors or aggressive price negotiations by major customers.
None identified
Faster-than-expected capacity increases from competitors or aggressive price negotiations by major customers leading to a collapse in gross margins.