Technology company IBM has developed the world’s first sub-1 nanometer (nm) chip technology, a breakthrough that could deliver faster and more energy-efficient processors for artificial intelligence (AI), cloud computing, and future electronic devices.
The new chip uses a design called nanostack and packs nearly 100 billion transistors into a chip about the size of a fingernail. That’s almost twice as many transistors as IBM’s 2 nm chip introduced in 2021. Transistors are tiny switches that process information inside a chip. In general, the more transistors a chip has, the more work it can do.
IBM said the new technology could deliver up to 50% better performance or use 70% less power than its 2 nm chips. That could help lower electricity costs in AI data centers while making future phones, laptops, and other devices more powerful.
The development comes as chipmakers are finding it increasingly difficult to make computer chips smaller using today’s manufacturing methods. IBM’s new three-dimensional nanostack design offers another way to keep improving chip performance instead of simply shrinking individual components.
“IBM’s latest chip breakthrough marks a landmark moment in computing, pushing technology beyond the nanometer era to the scale of atoms. With our new nanostack architecture, we’re not just making smaller transistors, we’re reinventing how chips are built to deliver dramatically more power and energy efficiency,” said Jay Gambetta, director of IBM Research and IBM Fellow. “This industry-first innovation continues IBM’s legacy of leading in next-generation technologies and sets the foundation for the next era of computing.”
Instead of arranging transistors side by side, IBM stacks them vertically, allowing more computing power to fit into the same amount of space while improving energy efficiency.
IBM also said research presented at VLSI 2026 showed the design can shrink a chip’s built-in memory, known as SRAM, by 40%. This would leave more room for processing power and help meet the growing demands of AI applications.
The company conducts semiconductor research with partners at its Albany, New York, research facility, including Lam Research Corp., Tokyo Electron (TEL), SCREEN Semiconductor Solutions Ltd., and ASML.
IBM expects the technology could be ready for commercial use within the next five years, paving the way for a new generation of smaller, faster, and more energy-efficient computer chips.