IBM NanoStack 0.7 nm Transistor
IBM says it has built the first transistor smaller than one nanometre, stacking them in three dimensions to fit nearly 100 billion onto a fingernail. It is the answer to a question every AI buyer keeps asking: does this keep getting cheaper?
On June 25, 2026 IBM announced that it had built a working transistor at 0.7 nanometres, which the industry also writes as the 7 angstrom node. It is the first time anyone has published a transistor below one nanometre.
The trick has a name: NanoStack. Instead of laying transistors out side by side on a flat surface and trying to make each one smaller, IBM stacks them vertically and staggers them, the way a car park adds floors instead of buying more land. Each stacked layer can even use different materials, so one layer can be tuned for speed and another for low power.
The numbers against the 2 nm chip
Why a Power buyer should keep half an eye on it
The Spyre Accelerator is built on a 5 nanometre process. The NanoStack work is three full generations beyond that. Nothing about it changes what you can buy this year, but it is a direct answer to the fear that AI hardware costs and power bills only ever go up.
The work happens at the Albany NanoTech Complex in New York, with Lam Research, Tokyo Electron, SCREEN Semiconductor Solutions, and ASML named as partners. IBM says production is possible as early as the next five years, which in semiconductor language means do not plan around it.
This is a laboratory result with a five-year horizon, announced by IBM and not yet independently manufactured at volume. It belongs in a strategy conversation, never in a purchase order.
Related
IBM NorthPole
A research chip with no separate memory at all. NorthPole claims 25 times the energy efficiency of a conventional design by refusing to move data, and IBM has already run a Granite model on it.
IBM Spyre Accelerator for Power
A 75 watt PCIe card that adds more than 300 TOPS of AI inference to a Power 11 server. It is the only IBM AI chip an AS/400 shop can actually order as an add-on, and it comes with a short list of things it refuses to work without.
IBM Artificial Intelligence Unit (AIU)
The research chip that became the card you can order. The AIU is why the Spyre Accelerator has 32 cores and why those cores look so much like the AI engine already inside an IBM Z processor.
Power 11 Matrix Math Acceleration
The AI acceleration most AS/400 shops already own and have never switched on. It is inside every core of the processor, it costs nothing extra, and it is the cheapest honest answer to a first AI pilot.