PCMag editors select and review products independently. If you buy through affiliate links, we may earn commissions, which help support our testing.

IBM Unveils 2-Nanometer Chip Process, But Actual Products Are Still Years Away

IBM says it's successfully prototyped the technology. However, it still needs to go through the long process of making the 2nm chip fabrication reach volume production.

 & Michael Kan Principal Reporter

Our team tests, rates, and reviews more than 1,500 products each year to help you make better buying decisions and get more from technology.

Our Expert
LOOK INSIDE PC LABS HOW WE TEST
65 EXPERTS
43 YEARS
41,500+ REVIEWS

(Credit: IBM)


IBM is introducing computer chips built with a "2 nano-meter" manufacturing process, but don’t expect the technology to go into volume production until late 2024.

IBM said the prototype technology had successfully fabricated 2nm-made chips on a silicon wafer at the company’s Albany, New York, lab. The manufacturing promises to make computer chips for smartphones, laptops, and servers more powerful and energy efficient. According to IBM, the 2nm process can improve a semiconductor's performance by 45% compared to the 7nm process from the current leading providers—an apparent reference to TSMC, which builds AMD and Apple chips.

IBM adds that the same 2nm technology can create a processor that uses 75% less power than a 7nm chip while maintaining the same performance. 

A closer view of 2nm chips on the silicon wafer
A closer view of 2nm chips on the silicon wafer. (Credit: IBM)

Still, comparing one company’s processor technology to another is tricky. Chip makers routinely talk about their 10nm, 7nm, and 5nm nodes, in their efforts to pack more and more transistors on a piece of silicon. However, the nanometer nomenclature is often just marketing speak that can obfuscate a real measure of computing performance: the actual transistor density on a chip.

IBM touting its 2nm process is certainly exciting. But based on the company’s slides, there actually isn’t a component on the chip at a 2nm size. Instead, the announcement is more about a generational improvement from IBM's earlier 5nm process, which debuted in 2017. 

IBM slide
Credit: IBM

According to IBM, the new 2nm process is capable of fitting 50 billion transistors on a chip the size of a fingernail—up from the 30 billion transistors on the 5nm node. 

Mukesh Khare, the company’s VP of Hybrid Cloud Research, added that the 2nm technology itself encompasses several chip advancements for the increased transistor density. “The key innovation that we are sharing here is a nanosheet enhancement with features like a Bottom Dielectric Isolation, a new lithography in front end,” he said. “So it’s like a combination of many breakthroughs to come together to form this 2nm node technology.”

Khare said IBM itself won’t be manufacturing the 2nm chips. Instead, the company plans on tapping partners including Samsung to build the processors. Whether Intel, which recently announced a research collaboration with IBM on semiconductor technology, will also use the technology is less clear. 

“We really welcome Intel as a partner in our ecosystem,” Khare said, without elaborating. “All the partners who are part of this ecosystem will benefit from this innovation.” 

The other issue is the competition. TSMC is also working to build chips with its own 2nm process for mass production in 2024, according to media outlets in Taiwan. In addition, the company is a proven foundry that's even attracted customer orders from Intel.

In the meantime, IBM plans on spending the next three years refining the 2nm process and ironing out any potential defects. “It takes a lot of effort to get from here to manufacturing,” Khare added.

About Our Expert

Michael Kan

Michael Kan

Principal Reporter

My Experience

I've been a journalist for over 15 years. I got my start as a schools and cities reporter in Kansas City and joined PCMag in 2017, where I cover satellite internet services, cybersecurity, PC hardware, and more. I'm currently based in San Francisco, but previously spent over five years in China, covering the country's technology sector.

Since 2020, I've covered the launch and explosive growth of SpaceX's Starlink satellite internet service, writing 600+ stories on availability and feature launches, but also the regulatory battles over the expansion of satellite constellations, fights with rival providers like AST SpaceMobile and Amazon, and the effort to expand into satellite-based mobile service. I've combed through FCC filings for the latest news and driven to remote corners of California to test Starlink's cellular service.

I also cover cyber threats, from ransomware gangs to the emergence of AI-based malware. In 2024 and 2025, the FTC forced Avast to pay consumers $16.5 million for secretly harvesting and selling their personal information to third-party clients, as revealed in my joint investigation with Motherboard.

I also cover the PC graphics card market. Pandemic-era shortages led me to camp out in front of a Best Buy to get an RTX 3000. I'm now following how the AI-driven memory shortage is impacting the entire consumer electronics market. I'm always eager to learn more, so please jump in the comments with feedback and send me tips.

The Best Tech I've Had:

  • My first video game console: a Nintendo Famicom
  • I loved my Sega Saturn despite PlayStation's popularity.
  • The iPod Video I received as a gift in college
  • Xbox 360 FTW
  • The Galaxy Nexus was the first smartphone I was proud to own.
  • The PC desktop I built in 2013, which still works to this day.

Read full bio