Skip to main content

Powerful 2nm chips are set to launch in 2026

Global semiconductor foundry TSMC has just confirmed that its production of the 2-nanometer process node is on track. This means that computer chips with yet unseen power are on the horizon.

According to the current estimates, chips based on 2nm architecture will enter mass production in 2025.

TSMC wafers.
TSMC

The information comes from C.C. Wei, chief executive of the Taiwan Semiconductor Manufacturing Company (TSMC), and was disclosed during an earnings call. TSMC first confirmed that it’s been working on a 2nm process node in 2020, but it kept the details pretty scarce. This time, the company divulged a bit more about the node’s architecture and shared new updates on the planned road map.

Recommended Videos

A good amount of technical information was shared as part of the earnings call. The new N2 node will rely on gate-all-around (GAA) transistors, which marks a change from its current Fin Field-Effect Transistor (FinFET) structure. The nodes will continue being fabricated based on extreme ultraviolet (EUV) lithography.

Such technical details may not mean much to most end users, but TSMC hasn’t shared much in the way of expectations where performance is concerned. However, it’s not the first foundry to work on a 2nm process, and some of its competitors have already made some serious headway. IBM unveiled its first 2nm chip last year.

IBM’s breakthrough was significant. The manufacturer said that using its 2nm process, it was able to fit a massive 50 billion transistors into a fingernail-sized chip. That’s 20 billion more than the 5nm process had when IBM announced it in 2017.

IBM employee holds 2nm wafer.
IBM

All of the big manufacturers are slowly making their way toward smaller and smaller process nodes. Switching from 7nm to 5nm, and in the future, from 5nm to 3nm, will bring significant upgrades in terms of performance and thermals. Smaller transistors use less power, take up less space, and push the performance ceiling up as more cores can be stacked in a smaller chip.

The information was first shared by Tom’s Hardware. TSMC has consistently delivered process node upgrades around once every two years, with enhanced and customized versions of already existing nodes launching in between. This time around, it seems to have hit a bit of a delay. Wei confirmed that while the “progress is to our expectation,” the risk production will only begin around the end of 2024. Then, the chips will enter high-volume production (HVM) in 2025, probably around the second half of the year, or even the end of it.

Switching to 2nm could result in performance we can’t imagine in consumer computers with today’s hardware, but we will have to wait. Although the chips are on track to start being mass-produced in 2025, it’s unlikely that we will see them in our PCs sooner than the second half of 2026. It’s a long road before the 2nm process is included in products that make it to market.

Monica J. White
Monica is a computing writer at Digital Trends, focusing on PC hardware. Since joining the team in 2021, Monica has written…
Here’s how the M3 Max chip compares to the most powerful Windows laptops
The 14-inch MacBook Pro with M3 Max chip seen from behind.

Apple's M3 Max is an incredibly powerful chip, significantly increasing Apple Silicon's CPU and GPU performance. It's gotten a ton of press, but is it necessarily faster than the fastest Windows laptops?

To find out, we pitted it against the Lenovo Legion 9i, a gaming laptop equipped with the ultrafast Intel Core i9-13980HX and Nvidia GeForce RTX 4090, and the Asus ROG Strix Scar 17 with the AMD Ryzen 9 7945HX and the RTX 4090. We can't compare the MacBook Pro 14 with the M3 Max directly to the Lenovo and Asus in that many benchmarks, particularly gaming, due to limits in testing and cross-platform compatibility. But we could compare enough to get an idea of how these various chips stack up against each other.
A brief look at architectures
The Apple M3 Max is an ARM-based system on a chip (SoC) currently at the high end of Apple Silicon's lineup. It represents the first chips made using a 3nm process and redesigned GPU architecture. On the CPU side, Apple increased the speed of its performance cores by 15% and its efficiency cores by 30% over the M2. Overall, Apple is promising a 20% to 25% improvement in performance. On the GPU side, Dynamic Caching is one technology that speeds up a variety of GPU processes, while gamers will benefit from mesh shading and hardware-accelerated ray tracing.

Read more
Why the most powerful laptops of 2024 might not use Intel’s latest chips
The Dell XPS laptop seen from behind, with the chassis half open.

Intel's about to add a whole lot of new chips to its list of top processors, and we just got a peek at a few of them out in the wild ahead of time. According to a new leak, upcoming Dell XPS and Alienware laptops will feature some of Intel's latest Meteor Lake CPUs, including the Core Ultra 7 and Core Ultra 9. However, Intel's previous-gen Raptor Lake processors are also making a surprising appearance in the lineup, which isn't a great sign.

Windows Report posted an exclusive leak that shows us a whole range of high-end laptops, which the publication predicts should be announced during CES 2024. This includes ultrathin Dell XPS 13, 14, and 16 laptops, but there are plenty of options for gamers too, including the Alienware m16 R2, x16 R2, and m18 R2. All of these laptops are said to feature Nvidia's best GPUs from the RTX 40-series.

Read more
Meet the Qualcomm chips powering Meta’s Quest 3 headset
Alan Truly holds a display model of Qualcomm's Snapdragon XR2 Gen 2 chip.

A display model of Qualcomm's Snapdragon XR2 Gen 2 chip. Tracey Truly / Digital Trends

Qualcomm just announced two new Snapdragon chips, one that dramatically increases the performance available to next-generation VR headsets, and another that expands the capabilities of new smart glasses.

Read more