News
CAPACITY TEST:

SK Hynix Nasdaq Debut Raises $26.5 Billion For AI Memory Capacity

Newsroom brief

Tech Wire Asia said SK Hynix is raising about $26.5 billion through a Nasdaq listing to fund Korean fabs and packaging capacity, while also flagging a 200% share run and memory-cycle risk.

Verified against source materialEdited by SendTech Times Chips & Compute Desk
SK Hynix Nasdaq Debut Raises $26.5 Billion For AI Memory Capacity
Image source: Tech Wire Asia

Tech Wire Asia said SK Hynix's planned Nasdaq debut gives U.S. investors a direct AI memory listing, while the article also points to a cycle risk after a 200% share run-up.

SK Hynix Nasdaq Listing Raises $26.5 Billion For Korean Chip Capacity

SK Hynix is using a U.S. listing to fund Korean semiconductor capacity rather than to cash out existing holders.

Tech Wire Asia listed the Nasdaq proceeds at approximately $26.5 billion and said trading in the American depositary receipts was set to begin under the ticker SKHY.

The same article said the debut would be the largest U.S. stock-market listing by a foreign company, ahead of Alibaba's $21.8 billion listing in 2014.

It also said only SpaceX's IPO last month ranked as a larger share sale anywhere.

SK Hynix priced the ADRs at $149 apiece, according to the article.

The deal puts a high-bandwidth-memory supplier directly in front of U.S. public-market investors at a time when AI accelerator demand has made memory supply a central constraint for chip buyers.

Cornerstone Investors Indicated Interest In Up To $7 Billion Of ADRs

Tech Wire Asia named three cornerstone-investor groups for the ADR sale: Baillie Gifford Overseas, Coatue-managed funds, and Situational Awareness Partners.

Tech Wire Asia said they collectively indicated interest in up to $7 billion of the ADRs, and identified Situational Awareness Partners as the AI infrastructure fund founded by former OpenAI researcher Leopold Aschenbrenner.

Tech Wire Asia said the Seoul-listed stock had climbed more than 200% this year and put SK Hynix's market value past $1 trillion.

The listing therefore reaches U.S. public-market investors after a large move in the underlying shares, while the proceeds remain tied to semiconductor capacity.

The proceeds are earmarked for two Korean facilities: a new semiconductor fabrication plant and an advanced chip-packaging site.

For equipment, SK Hynix pointed to an 11.9 trillion won EUV purchase plan, with installation due by the end of next year.

HBM Share And AI Customers Carry The Valuation Case

According to Tech Wire Asia, SK Hynix held an estimated 50 to 55% of the HBM market.

It named Nvidia and Alphabet's Google as major customers for the memory supplier.

KAIST electrical engineering professor Yoo Hoi-jun was quoted as calling the company indispensable while demand for GPUs and AI data centres holds.

Tech Wire Asia said U.S. investors previously had Micron as the main direct public-market route into AI memory.

Analysts cited by Tech Wire Asia expect access to a larger pool of investors to lift SK Hynix's valuation closer to Micron's, while Samsung's memory business remains listed only in Seoul.

The same article also compared the listing route with TSMC's New York premium over Taipei.

It framed the parallel as a precedent for how a U.S. listing can broaden access to global funds, not as proof that SK Hynix will receive the same valuation effect.

Memory-Cycle Risk Remains After The Share Rally

The article kept a caveat around DRAM cycles.

It said memory booms have historically carried busts, and that a 200% share run leaves good news already reflected in the price.

Tech Wire Asia said SK Hynix's first earnings as a dual-listed company are the next disclosed test.

The article said consensus expected revenue of around 83 trillion won, but it did not disclose named long-term supply commitments, signed customer volumes, utilisation targets for the new plants, or a timetable for revenue from the added Korean capacity.

Share this article
inXf

Related articles

More
Micron And Anthropic Put AI Memory Supply Inside Claude’s Compute Plan
Chips & Semiconductors

Micron And Anthropic Put AI Memory Supply Inside Claude’s Compute Plan

Micron and Anthropic signed a strategic agreement covering AI memory and storage architecture, supply, Claude adoption inside Micron and a Series H investment.

SK Hynix Plans Nasdaq ADR As AI Memory Demand Lifts Fundraising
Chips & Semiconductors

SK Hynix Plans Nasdaq ADR As AI Memory Demand Lifts Fundraising

SK Hynix plans a Nasdaq ADR listing that could raise 45.45 trillion won, giving global investors a new route into AI memory demand while capacity plans remain tied to Korea and Indiana.

Micron Rally Signals AI Memory Shortage In Data-Centre Buildout
Chips & Semiconductors

Micron Rally Signals AI Memory Shortage In Data-Centre Buildout

Micron's market rally is being driven by AI data-centre memory demand, with TechCrunch citing a $1.27 trillion market cap, a 236% one-month stock gain and supply shortages expected to last into 2027.

South Korea Chip Plan Names 800 Trillion Won Without Funding Split
Chips & Semiconductors

South Korea Chip Plan Names 800 Trillion Won Without Funding Split

South Korea announced an 800 trillion won ($520 billion) public-private semiconductor investment plan with Samsung Electronics and SK Hynix. The plan centers on four production facilities and HBM capacity, but it does not specify how much money will come from the state, Samsung or SK Hynix.

SK hynix Expert Frames AI Chip Race Around Power, Water And Megafabs
Chips & Semiconductors

SK hynix Expert Frames AI Chip Race Around Power, Water And Megafabs

An SK hynix Newsroom expert column argues that AI semiconductor competition is moving beyond faster chips toward megafab capital, grid delivery, industrial water and memory supply stability.

Micron Locks AI Memory Buyers Into Long-Term Supply Deals
Chips & Semiconductors

Micron Locks AI Memory Buyers Into Long-Term Supply Deals

Micron said fiscal third-quarter revenue reached $41.46 billion and outlined 16 long-term customer agreements as AI data center demand keeps memory supply tight into 2028.

Keep Reading

More Stories

Latest
Burjeel Sukuk Draws $1.6 Billion Order Book For AI Healthcare PlansCapital & PolicyJul 10, 2026Burjeel Sukuk Draws $1.6 Billion Order Book For AI Healthcare PlansBurjeel Holdings listed a $500 million sukuk on the London Stock Exchange after a $1.6 billion order book, but did not name the AI healthcare projects or digital budget tied to the proceeds.IBM Bob Adds Multi-Agent AI Controls For Legacy Software WorkAIJul 10, 2026IBM Bob Adds Multi-Agent AI Controls For Legacy Software WorkIBM has expanded Bob with multi-agent coordination, Bobalytics cost analytics and premium IBM Z, IBM i and Java workflows, while customer performance claims still lack independent benchmark detail.Microsoft Says AI Datacentres Drove 25 Percent Emissions RiseCloud & Data CentersJul 10, 2026Microsoft Says AI Datacentres Drove 25 Percent Emissions RiseMicrosoft said total Scope 1, Scope 2 and Scope 3 emissions rose 25 percent year over year in FY25, driven primarily by datacentre infrastructure expansion. The company matched 100 percent of annual global electricity consumption with renewable energy, but said AI infrastructure demand for energy, water, land and materials is still outpacing sustainability solutions.Injective SDK npm Compromise Exposes Wallet-Key Theft RiskCybersecurityJul 10, 2026Injective SDK npm Compromise Exposes Wallet-Key Theft RiskSocket, Ox Security and StepSecurity said they detected wallet-stealing code in @injectivelabs/sdk-ts npm package version 1.20.21 after an Injective Labs contributor account was compromised. Socket said the malicious release was downloaded 310 times before deprecation, while Ox Security counted 87 direct dependencies and described a six-figure cumulative download count across dependent packages.SEC Novel ETF Review Draws Early Pushback Over Prediction MarketsFintech & Digital PaymentsJul 10, 2026SEC Novel ETF Review Draws Early Pushback Over Prediction MarketsThe SEC is asking whether novel ETFs should be allowed to move further into cryptocurrencies and prediction markets. Early commenters warned against event-contract ETFs, while Roundhill, Bitwise and GraniteShares proposals remain unresolved.Morgan Stanley Sees AI Capital Rotation Towards HyperscalersCapital & PolicyJul 10, 2026Morgan Stanley Sees AI Capital Rotation Towards HyperscalersEconomy Middle East cited IDC's forecast for semiconductor revenue to reach $1.29 trillion in 2026 and said Morgan Stanley sees AI-market leadership rotating from chipmakers towards hyperscalers. The article did not disclose Morgan Stanley's index levels, portfolio weights, hyperscaler capex assumptions or customer-level AI return evidence.Intel Dunlow Manifests Point To 28-Core Nova Lake-S Xeon PlatformChips & SemiconductorsJul 10, 2026Intel Dunlow Manifests Point To 28-Core Nova Lake-S Xeon PlatformTom's Hardware reported that NBD shipment manifests point to an Intel Dunlow workstation and entry-server platform with up to 28 cores, LGA1954 packaging, dual-channel memory and 95W processor base power. The details remain pre-launch documentation, and Intel has not confirmed launch dates, pricing, core mix or customers.MAS Proposes Three-Week Route For Repeat Singapore Retail FundsCapital & PolicyJul 10, 2026MAS Proposes Three-Week Route For Repeat Singapore Retail FundsMAS is consulting on an Alternative Funds Appendix for Singapore retail fund products. The regulator said most new fund categories could take about three months to assess, while later funds of the same type could be authorised within three weeks.AWS GraphRAG Deployment Claims 87 Percent Drug Research Cycle CutAIJul 10, 2026AWS GraphRAG Deployment Claims 87 Percent Drug Research Cycle CutAI News reported an AWS GraphRAG deployment that cut drug research cycles by 87 percent and moved six-month discovery work to three weeks. The account did not name customers, publish benchmark methodology or disclose Bedrock token costs.Humain Sets Aside 50 Megawatts Of Saudi Compute For Cohere ModelsCloud & Data CentersJul 10, 2026Humain Sets Aside 50 Megawatts Of Saudi Compute For Cohere ModelsHumain will designate at least 50 megawatts of dedicated compute capacity for Cohere foundational models, the companies said. The Saudi-backed AI company expects the expansion to be live by late 2027, but the announcement did not disclose the site, power supplier, pricing or hardware mix.Cerebras Plans 8x To 10x Manufacturing Scale-Up For AI InferenceChips & SemiconductorsJul 10, 2026Cerebras Plans 8x To 10x Manufacturing Scale-Up For AI InferenceCerebras chief executive Andrew Feldman said the company plans to scale manufacturing capacity by 8x to 10x this year and claimed its systems can run inference 10, 15, 20 or 30 times faster than GPUs. The interview-led source named customers including AlphaSense, Cognition AI, OpenAI, Block and GlaxoSmithKline, but did not include third-party benchmark methodology.Swift Lines Up 17 Banks For Tokenised Deposit Ledger TestsFintech & Digital PaymentsJul 10, 2026Swift Lines Up 17 Banks For Tokenised Deposit Ledger TestsSwift said 17 banks are preparing to test live transactions on a blockchain-based shared ledger for tokenised deposits. The system is meant to support round-the-clock cross-border payments, while final settlement remains tied to existing payment systems.