By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
Panelists agree that Micron's high gross margin guidance signals pricing power, but they caution about execution risks, cyclical peaks, and potential margin erosion due to increased competition and demand normalization. The stock's valuation is seen as vulnerable to any margin slip or inventory build.
Risk: Massive capex program and potential margin compression due to increased competition and demand deceleration.
Opportunity: Sustaining high gross margins and cash generation from HBM sales.
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 →
Memory specialist Micron Technology (NASDAQ: MU) is scheduled to report its fiscal third-quarter results on Wednesday, June 24, after the market closes. And expectations heading into the report are about as high as they get. Shares have surged 244% in 2026, crossing a $1 trillion market capitalization along the way -- a milestone only two other memory companies have reached.
That run has been powered by an artificial intelligence (AI) build-out that has turned memory chips into one of the most sought-after components in the data center, and Micron into one of its biggest beneficiaries. But a stock that has climbed this far, this fast, leaves little room for a stumble.
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 »
Put another way, the stakes are high. And when the company reports later this month, a single number may tell investors more about whether the story is still intact than any other line in the release.
That number is gross margin.
Here's a closer look at why this one metric carries so much weight -- and what to watch as the report approaches.
When Micron last reported, in March, its results were staggering across the board. Fiscal second-quarter revenue (the period ended Feb. 26, 2026) nearly tripled year over year to $23.86 billion, marking a company record. But the figure that best captured what's happening inside the business was gross margin, which expanded to about 75% from roughly 37% a year earlier. That is an enormous swing for a memory company, and it speaks directly to pricing.
Memory has historically been a brutal, commodity-like business, with prices swinging sharply as supply and demand fall in and out of balance. What's different now is that AI demand has collided with tight industry supply, sending prices higher and lifting margins along with them. In the fiscal second quarter, Micron said DRAM prices sequentially rose in the mid-60% range, and NAND prices climbed in the high-70% range.
For the fiscal third quarter, management guided for gross margin to reach about 81%. That would mark yet another step up. And it explains why this is the make-or-break figure: revenue can grow on volume alone, but a gross margin approaching 81% is a direct readout of how much pricing power Micron still holds.
If that number comes in at or above guidance, it confirms the favorable pricing environment is holding. If it slips, it could signal that the best of the pricing cycle is already behind the company.
"We expect higher price, lower cost and favorable mix to all contribute to gross margin expansion in Q3," said Micron chief financial officer Mark Murphy in the company's fiscal second-quarter earnings call.
That is the bar the report will be measured against.
The bull case rests on supply that simply can't keep up. High-bandwidth memory (HBM), a specialized type of DRAM that sits alongside AI processors, has become the tightest part of the chain -- and Micron has said its entire 2026 HBM supply is already sold out. That kind of visibility is rare for a chipmaker, and it suggests pricing could stay firm well into next year. And management has even gone further, saying it expects supply and demand for both DRAM and NAND to remain tight beyond calendar 2026.
There's also a structural argument. As AI models grow larger and lean more heavily on memory, the demand for Micron's chips may prove more durable than in past cycles.
"In the AI era, memory has become a strategic asset for our customers," said Micron CEO Sanjay Mehrotra when the company reported in March, pointing to the same dynamic that has reshaped the business.
The bear case is the one that has repeatedly plagued memory stocks: cyclicality. Micron has lived through painful downturns before -- most recently in 2023, when oversupply cratered prices and the company posted losses. And rivals Samsung and SK Hynix are notably racing to expand their own HBM output, and Micron itself is projecting more than $25 billion in capital spending this fiscal year. Should that supply arrive faster than AI demand can absorb it, the same pricing leverage now lifting margins could just as easily work in reverse.
So, what should investors make of all this heading into June 24?
With shares trading at a trailing price-to-earnings ratio in the mid-40s after their enormous run, a lot of good news is already baked in. I think the smartest approach is to keep your eyes on that gross margin line rather than the headline revenue number. It may be the best signal of whether Micron's pricing power -- and the thesis behind the stock's remarkable climb -- is still intact.
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 $433,268! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,259,391!
Now, it’s worth noting Stock Advisor’s total average return is 935% — 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 13, 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. 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
"High-40s P/E leaves scant margin for error if gross margins miss 81% or HBM supply from rivals accelerates."
The article correctly flags gross margin as the key signal for MU's pricing power amid AI-driven DRAM/NAND tightness, with 81% guided for Q3 and 2026 HBM already sold out. Yet it underplays execution risk from $25B+ capex this year and rivals Samsung/SK Hynix aggressively scaling HBM output. At mid-40s trailing P/E after a 244% run, any sequential margin slip or inventory build could trigger rapid de-rating even if revenue beats, given memory's history of abrupt cycle reversals once supply catches demand.
AI model scaling could sustain structural memory demand well beyond 2026, keeping HBM allocation tight regardless of competitor ramps and validating the 75-81% margin step-up as a new baseline rather than peak-cycle noise.
"Micron’s upside hinges on a temporary pricing power spike; any softer AI demand or faster-than-expected supply expansion could snap margins back, triggering multiple compression despite the strong headline revenue outlook."
Micron’s Q3 guide implying around high-80s gross margins suggests pricing power linked to AI-driven demand and tight supply (HBM in particular). Yet this could be a cyclical peak: rival capex (Samsung, SK Hynix) and potential AI demand normalization could erode pricing power sooner than the stock anticipates, especially if 2026 supply constraints ease or replacement demand falters. The narrative hinges on memory as a strategic AI asset, but that story can unwind quickly if demand slows, inventories build, or cost-per-bit declines resume post-cycle. The stock’s steep year-to-date run and lofty valuation imply limited downside protection if margins don’t hold, making a cautious stance prudent.
If AI demand remains extraordinarily tight and all players struggle to ramp supply, margins could stay elevated longer than skeptics expect, supporting higher multiples.
"Micron's $25 billion CapEx strategy creates a significant risk of oversupply that the current 81% gross margin guidance fails to account for."
Focusing solely on gross margin as the 'make-or-break' metric is a classic trap for cyclical memory stocks. While an 81% target is impressive, it represents a peak-cycle anomaly. The real risk isn't just margin compression; it is the massive $25 billion capital expenditure (CapEx) program. Micron is aggressively chasing capacity in a sector where supply-side discipline has historically been the first thing to break. If HBM demand shows even a minor deceleration, those billions in new, specialized equipment will become expensive, underutilized assets. I am neutral because the valuation already prices in a 'forever-growth' scenario for AI memory, ignoring the inevitable return of supply-side competition.
If HBM truly becomes a structural, non-commodity bottleneck for AI, Micron’s pricing power may not be cyclical at all, but a permanent shift to a higher-margin, software-like business model.
"MU's valuation already prices in a perfect Q3; the stock's fate depends on forward guidance signaling margin sustainability beyond 2026, not on beating a number already embedded in a 45x multiple."
The article's focus on gross margin as the 'make-or-break' metric is sound—81% guidance vs. 75% actual would confirm pricing power. But the framing misses critical timing risk: MU trades at 45x trailing P/E after a 244% YTD run. Even if Q3 margins hit 81%, that's already priced in. The real risk isn't margin miss—it's forward guidance. If management signals margin deceleration in Q4 or fiscal 2027 (even while staying profitable), the stock reprices sharply. HBM sold-out through 2026 sounds bullish until you remember Samsung and SK Hynix are ramping capacity simultaneously. The article treats supply tightness as durable; history suggests it's cyclical. A beat on Q3 margins could paradoxically trigger selling if guidance suggests the peak is near.
If gross margin actually expands to 81% or beyond and management reaffirms 2026 HBM sell-out, the stock could re-rate higher on proof the AI supercycle is structural, not cyclical—especially if competitors' capacity comes online slower than feared.
"HBM-specific capex converts to faster FCF payback than commodity DRAM builds, muting stranded-asset concerns."
Gemini flags capex as stranded-asset risk but ignores that HBM lines carry 2-3x the ASP and 90%+ utilization via multi-year contracts already signed through 2026. That shifts the payback profile: incremental depreciation hits earnings yet cash generation accelerates once the new capacity is online, unlike prior DRAM cycles where utilization collapsed. The $25B spend may therefore compress rather than expand the valuation multiple if margins hold.
"Capex-driven margins depend on persistently high HBM demand; a demand slowdown or faster capacity ramp could compress margins and extend the payback, challenging the current valuation."
You're optimistic that $25B of HBM capex yields durable utilization and a payback lift under any demand scenario. The flaw is assuming multi-year contracts and 90%+ utilization persist if AI demand cools or rivals ramp faster. Capex raises depreciation and financing costs, and a faster supply rebound could compress margins even with 81% guidance. The stock is priced for perfection; a soft landing could trigger a sharp re-rating.
"HBM contracts provide a false sense of security, as hyperscalers may force contract renegotiations or pivot to custom silicon, rendering Micron's massive capex a liability."
Grok, your focus on multi-year contracts ignores the 'take-or-pay' reality. If hyperscalers like AWS or Microsoft pivot their AI infrastructure strategy, those contracts are often renegotiated or breached, leaving Micron with the bill. Gemini is right to fear the capex, but misses the secondary risk: the shift toward custom HBM-integrated chips. Micron risks becoming a low-margin foundry for custom silicon rather than a high-margin product leader if they lose the architectural race to internal development.
"The valuation already embeds margin compression; a Q3 beat only matters if 2027 guidance signals structural durability, not cyclical peak."
Gemini's custom-silicon risk is real but overstated. Micron supplies HBM to hyperscalers' own AI chips (NVIDIA's H100/H200 use external HBM), not just foundry work. The architectural race isn't Micron vs. internal dev—it's whether HBM remains a discrete, high-ASP component or gets monolithically integrated. That's a 5-7 year shift, not imminent. More pressing: ChatGPT's 'priced for perfection' claim ignores that 45x trailing P/E on $9B LTM earnings assumes margin normalization to ~65% by 2026, not 81% forever. A beat with flat guidance doesn't trigger selling—only forward deceleration does.
Panelists agree that Micron's high gross margin guidance signals pricing power, but they caution about execution risks, cyclical peaks, and potential margin erosion due to increased competition and demand normalization. The stock's valuation is seen as vulnerable to any margin slip or inventory build.
Sustaining high gross margins and cash generation from HBM sales.
Massive capex program and potential margin compression due to increased competition and demand deceleration.