0.7 nm (7 angstrom) node using a 3D nanostack architecture that vertically stacks transistors, fitting nearly 100 billion transistors on a fingernail-sized chip. Projected up to 50% more performance or 70% better efficiency versus the 2 nm node.
IBM Research's 0.7 nm (7 angstrom) chip technology using a 3D "nanostack" transistor architecture, announced June 2026.
Updated EU status checked Last shown
IBM sub-1nm chip technology (nanostack) at a glance
- What is IBM sub-1nm chip technology (nanostack)?
- IBM sub-1nm chip technology (nanostack) is a hardware from IBM. IBM Research's 0.7 nm (7 angstrom) chip technology using a 3D "nanostack" transistor architecture, announced June 2026.
- Who makes IBM sub-1nm chip technology (nanostack)?
- IBM sub-1nm chip technology (nanostack) is made by IBM.
- Does IBM sub-1nm chip technology (nanostack) work in the EU?
- Unverified. No explicit evidence found. This is a research-stage chip technology with no commercial availability or regional offering yet. Last verified 14 Nov 2026.
- How much does IBM sub-1nm chip technology (nanostack) cost?
- Pricing unknown. Research demonstration; not commercially available. Licence: Proprietary.
- Where was IBM sub-1nm chip technology (nanostack) shown?
- In 1 creator video by AI Search. Most recently by AI Search on 28 Jun 2026, at 11:35 in “GPT 5.6, Mythos ban lifted, realtime avatars, Seedance 2.5, brain ultrasound: AI NEWS”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
IBM's sub-1 nm chip technology is a semiconductor research result announced on 25 June 2026 at the 0.7 nm (7 angstrom) node. It is built on "nanostack", which IBM describes as the industry's first known three-dimensional, nanosheet-based transistor design. Nanostack vertically stacks and staggers transistors using 3D sequential integration and allows different material combinations in each stacked layer.
IBM says the chip packs nearly 100 billion transistors onto a fingernail-sized die, nearly twice the density of its 2 nm chip unveiled in 2021. Published technical results project up to 50% more performance or 70% greater energy efficiency compared with IBM's 2 nm node chips. Research presented at VLSI 2026 reported 40% scaling in SRAM. Experimental validation covered ultra-thin dielectric bonding in CMOS integration, dual-channel engineering and a functional CMOS inverter. The performance figures are projections.
This is a research demonstration, not a purchasable product. IBM says it sees a path to production as early as the next 5 years. The work is done with partners at the Albany, New York research facility, including Lam Research, Tokyo Electron and SCREEN, on High NA EUV processes using ASML tooling. IBM notes that node names refer to a manufacturing generation rather than an exact physical dimension.
- 0.7 nm (7 angstrom) node logic technology
- 3D nanostack architecture with vertically stacked and staggered transistors
- Nearly 100 billion transistors on a fingernail-sized chip
- Projected up to 50% more performance or 70% better energy efficiency than 2 nm
- 40% SRAM scaling reported at VLSI 2026
- Production path projected within about 5 years
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Similar AI tools
Closest neighbours by meaning, not just by category.
Majorana 2
Hardware · Microsoft
Microsoft's second-generation topological quantum chip with a lead-based materials stack, developed with Microsoft Discovery.
Room temperature magnetic semiconductors discovery
Research · Vals AI
Vals AI report on AI agents using DFT simulations to find two room-temperature antiferromagnetic semiconductor candidates.
TPU 8t
Hardware · Google
Google's eighth-generation TPU for large-scale AI pre-training, scaling to 9,600 chips per superpod.
Cactus Needle 2
Model · Cactus
Tiny on-device tool-calling and extraction model from Cactus, shipped as an 8–29 MB binary for phones, wearables and microcontrollers.
Needle 3
Model · Cactus Compute
Tiny 29M–121M parameter on-device model for tool calling and extraction, shipped as an 8–29 MB binary.
Project Suncatcher
Hardware · Google
Google research initiative to put TPU-equipped satellites in orbit as a prototype space-based AI data center.