IBM unveils 0.7nm chip design with nearly 100 billion transistors

Source: mobileworldlive.comJune 25, 2026

IBM unveiled a 0.7nm silicon chip design in June 2026 with a 3D stacked architecture that fits nearly 100 billion transistors into a form factor the company said is about the size of a human fingernail.

TL;DR

  • IBM disclosed a 0.7nm chip design in June 2026.
  • The design uses a 3D stacked nanostack architecture.
  • IBM said the chip delivers nearly twice the density of its 2nm chip unveiled in 2021.
  • IBM cited potential gains of 50% in performance and 70% in energy efficiency versus its 2nm design.
  • Research presented at the Very-Large-Scale Integration Symposium indicated a 40% reduction in SRAM size and power consumption.

IBM said its 0.7nm design addresses physical manufacturing constraints by changing chip construction rather than only shrinking transistors. Jay Gambetta, director of IBM Research and an IBM Fellow, said the company is “reinventing how chips are built.”

IBM said the 0.7nm chip provides almost twice the density of the company’s 2nm chip unveiled in 2021. The company’s technical assessments indicated the design could improve performance by 50% and energy efficiency by 70% compared with that 2nm chip.

IBM said research presented earlier in June 2026 at the Very-Large-Scale Integration Symposium showed its nanostack architecture could reduce SRAM size and power consumption by 40%. IBM said the architecture arranges stacks vertically and staggers transistors to increase transistor count, and added that it validated the design through CMOS integration tests and demonstrations.

Related questions

  • What performance and efficiency gains did IBM cite for its 0.7nm chip design?
  • How does IBM’s nanostack architecture differ from nanosheet technology?
  • What SRAM reductions did IBM report from research presented at the Very-Large-Scale Integration Symposium?

More from Technology

Related Content

More articles and news tagged with: IBM, 0.7nm, 2nm, nanostack, SRAM, CMOS, Very-Large-Scale Integration Symposium

Related Articles

Related News