By Wayne Williams

Copyright techradar

Skip to main content

Tech Radar Pro

Tech Radar Gaming

Close main menu

the business technology experts

België (Nederlands)

Deutschland

North America

US (English)

Australasia

New Zealand

View Profile

Search TechRadar

Expert Insights

Website builders

Web hosting

Best web hosting
Best office chairs
Best website builder
Best antivirus
Expert Insights

Don’t miss these

Samsung’s biggest rival and Sandisk have come together to standardize High Bandwidth Flash memory – which could mean better AI performance for everyone

After Sandisk, D-Matrix is proposing an intriguing alternative to the big HBM AI puzzle with 10x better performance with 10x better energy efficiency

AMD gets ready for Nvidia Vera Rubin with 432GB MI400 GPU monster paired with 256-core EPYC Venice – I can’t wait to see the sparks fly

Nvidia has launched a GPU with 128GB of GDDR7 RAM but yeah, there’s no way it will sell one to us to run games

AI GPU accelerators with 6TB HBM memory could appear by 2035 as AI GPU die sizes set to shrink – but there’s far worse coming up

‘No asterisk generation’ : AMD promises its MI450 AI GPU will be faster than ANYTHING Nvidia has, yes, that includes even Rubin Ultra

AMD sheds more light on 128-GPU MI355X DLC rack that will deliver 2.4 Exaflop at FP4 precision – here’s how it compares with Nvidia’s flagship Vera Rubin

A win for consumers? SK Hynix confirms it will bring industry’s first 300+ layer QLC NAND to PCs first before moving to enterprise – but don’t expect cheap 8TB SSDs anytime soon

AMD unveils puzzling new MI355X AI GPU as it acknowledges there won’t be any AI APU for now

Rising prices of DDR4, DDR5, GDDR6 RAM set to cause havoc on PC, smartphone and GPU prices – and no, AI is not the one to be blamed

LPDDR6 likely to debut in 2026 as JEDEC publishes new standard document and targets mobile devices and AI – desktop PCs and workstations will have to wait

Sandisk recruits RISC cofounder, AMD graphics legend to spearhead cheaper rival to HBM — high bandwidth flash could bring SSD-capacities to AI GPUs without the cost

Here’s how Nvidia and AMD hardware are being used in surprising ways to build Nvidia’s fastest GPU ever

Towards the Giga IOPS pipedream: How Nvidia wants to reach 100 million IOPS – even if it means inventing totally new types of memory

Huawei released an AI SSD which uses a secret sauce to reduce the need for large amounts of expensive HBM

SK Hynix’s HBM4 will be the first out of the gate for Nvidia’s Rubin AI GPU, leaving Samsung and Micron in its wake

Wayne Williams

15 September 2025

Development is complete, and mass production is about to start

When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.

(Image credit: SK Hynix)

SK Hynix completes HBM4 development and prepares technology for mass production
Nvidia Rubin AI processors expected to feature SK Hynix’s new HBM4 chips
HBM4 doubles connections and improves efficiency by 40 percent

South Korean memory giant SK Hynix says it has completed development work on HBM4 and is now preparing the technology for mass production.

This puts it ahead of rivals Samsung and Micron, who are still developing their own versions.
The chips are expected to feature in Nvidia’s next-generation Rubin AI processors, and will play an important role in powering future artificial intelligence workloads.

You may like

Samsung’s biggest rival and Sandisk have come together to standardize High Bandwidth Flash memory – which could mean better AI performance for everyone

After Sandisk, D-Matrix is proposing an intriguing alternative to the big HBM AI puzzle with 10x better performance with 10x better energy efficiency

AMD gets ready for Nvidia Vera Rubin with 432GB MI400 GPU monster paired with 256-core EPYC Venice – I can’t wait to see the sparks fly

Beyond the AI infrastructure limitations
Joohwan Cho, Head of HBM Development at SK Hynix, said: “Completion of HBM4 development will be a new milestone for the industry. By supplying the product that meets customer needs in performance, power efficiency and reliability in timely manner, the company will fulfill time to market and maintain competitive position.”

High Bandwidth Memory, or HBM, stacks layers of DRAM vertically to accelerate data transfer.
Demand for high bandwidth memory has risen with the surge in AI workloads, and energy efficiency has become a pressing concern for data center operators.
HBM4 doubles the number of I/O connections compared with the previous generation and improves power efficiency by more than 40%.

Are you a pro? Subscribe to our newsletter
Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!
Contact me with news and offers from other Future brandsReceive email from us on behalf of our trusted partners or sponsorsBy submitting your information you agree to the Terms & Conditions and Privacy Policy and are aged 16 or over.
The Korean memory maker says this translates into higher throughput and lower energy use in data centers, with service performance gains of up to 69%.
HBM4 surpasses the JEDEC industry standard operating speed of 8Gbps by running above 10Gbps.
SK Hynix adopted its advanced MR-MUF process for stacking chips, which improves heat dissipation and stability, along with the 1bnm process technology to help minimize manufacturing risk.
Justin Kim, President and Head of AI Infra at SK Hynix, said: “We are unveiling the establishment of the world’s first mass production system of HBM4. HBM4, a symbolic turning point beyond the AI infrastructure limitations, will be a core product for overcoming technological challenges. We will grow into a full-stack AI memory provider by supplying memory products with the best quality and diverse performance required for the AI era in a timely manner.”
You might also like

SK Hynix chief says AI memory market set to boom as demand rises
Samsung archrival discloses more details about key AI memory tech, MBM4
Micron wants a bigger slice of the $100 billion HBM market with its 2026-bound HBM4

Wayne Williams

Social Links Navigation

Wayne Williams is a freelancer writing news for TechRadar Pro. He has been writing about computers, technology, and the web for 30 years. In that time he wrote for most of the UK’s PC magazines, and launched, edited and published a number of them too.

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.

Samsung’s biggest rival and Sandisk have come together to standardize High Bandwidth Flash memory – which could mean better AI performance for everyone

After Sandisk, D-Matrix is proposing an intriguing alternative to the big HBM AI puzzle with 10x better performance with 10x better energy efficiency

AMD gets ready for Nvidia Vera Rubin with 432GB MI400 GPU monster paired with 256-core EPYC Venice – I can’t wait to see the sparks fly

Nvidia has launched a GPU with 128GB of GDDR7 RAM but yeah, there’s no way it will sell one to us to run games

AI GPU accelerators with 6TB HBM memory could appear by 2035 as AI GPU die sizes set to shrink – but there’s far worse coming up

‘No asterisk generation’ : AMD promises its MI450 AI GPU will be faster than ANYTHING Nvidia has, yes, that includes even Rubin Ultra

Latest in Pro

Chinese malware is flooding GitHub pages – HiddenGh0st, Winos and kkRAT hit devs via SEO poisoning

CISA blasted by US watchdog for wasting funds and retaining the wrong employees

China launches probes into U.S. chip restrictions, citing discrimination and dumping concerns

Researchers uncover huge IPTV piracy network spanning 1,000 domains and 10,000 IP addresses – here’s what you need to know

AI has the potential to fix the developer experience – here’s now to make it happen

China accuses Nvidia of breaking anti-monopoly rules ahead of trade talks with US

Latest in News

Battlefield 6 will be better for everyone thanks to the Xbox Series S

Amazon teases major hardware launch – here are 5 things to expect, from new Echos to Kindles

I can’t stop rewatching Christopher Nolan’s best movie, and the good news? It’s free to stream

The Apple Watch’s new hypertension upgrade lands in watchOS 26 today – here’s why it’s a big deal and which models are compatible

Your Apple TV 4K gets a free upgrade to tvOS 26 today – here are 5 changes to try

Tesla scraps its cheapest Cybertruck after just five months – as it hurtles towards becoming one of the all-time biggest flops

LATEST ARTICLES

Asus launches ProArt studio router and switch built to move 8K files at lightning speed with zero workflow delays

Tesla scraps its cheapest Cybertruck after just five months – as it hurtles towards becoming one of the all-time biggest flops

Chinese malware is flooding GitHub pages – HiddenGh0st, Winos and kkRAT hit devs via SEO poisoning

This is the same AI image prompt 10 years apart – the evolution is incredible

Is it time to ditch Sonos for WiiM? How the two multi-room ecosystems compare – and whether you should switch

TechRadar is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site.

Contact Future’s experts

Terms and conditions

Privacy policy

Cookies policy

Advertise with us

Web notifications

Accessibility Statement

Future US, Inc. Full 7th Floor, 130 West 42nd Street,

Please login or signup to comment

Please wait…