IBM debuts world’s first sub-1 nanometer chip.
They just announced a 0.7nm chip technology.
(0.7nm is about 100,000 times thinner than a human hair, only a few atoms across as a technology marker,)
It stops treating smaller chips as a flat-layout problem and starts stacking transistors upward through a new nanostack architecture.
A chip node no longer means every feature has that exact size, but 7 angstroms means IBM is pushing transistor design into a scale where individual atoms start to shape the engineering limits.
Traditional scaling packs more switches side by side, while nanostack vertically staggers nanosheet transistors, letting each layer use different materials for speed or lower power instead of forcing one transistor recipe across the chip.
IBM says the design can fit nearly 100B transistors on a fingernail-sized chip, deliver up to 50% more performance or 70% better energy efficiency than its 2nm node, and shrink SRAM by 40%, which is huge because AI chips constantly wait on memory.
Practically it means future chips that can run bigger AI models, phones, laptops, servers, and cloud systems faster while using much less power, because more compute and memory can fit into the same tiny chip area.
---
newsroom. ibm. com/2026-06-25-ibm-debuts-worlds-first-sub-1-nanometer-chip-technology
