From www.techradar.com

Nvidia and MediaTek could be cooking up a powerful laptop CPU to blow away Snapdragon X Elite – or even Apple’s M4

(Image credit: Shutterstock / G-Stock Studio)

Qualcomm’s imminent Snapdragon X Elite and Plus CPUs are causing plenty of excitement, but they don’t exist in a vacuum – there are of course rivals in the laptop processor world, and perhaps another one is in the works from some big players.

As highlighted on X (formerly Twitter) by analyst Dan Nystedt (via Wccftech), there’s a report from Economic News Daily that contends that MediaTek and Nvidia are cooperating on a joint venture to make a chip that’ll be manufactured using TSMC’s 3nm process.

Rumor: MediaTek is working with Nvidia to co-develop an Arm-based AI processor for personal computers (PCs), media report, with the design to be finalized in the 3rd quarter, with verification in the 4th quarter, media report, noting the chip will be priced as high as US$300…May 13, 2024

This is just a rumor, mind, so put on your skeptical hat while considering the details – but it’s certainly plausible that these companies may want to get a slice of the action with the predicted explosion in AI PCs that’ll soon start.

With the design of this chip apparently due to be finalized in Q3 – so by the end of September 2024 – followed by testing in Q4, we’re told that manufacturing is slated to happen in the first half of 2025.

Apparently the SoC could be sold at around $300 per unit, so this is a premium piece of silicon made with an advanced (TSMC) process, meaning it’s presumably intended to seriously power up high-end AI PCs.

We could find out more soon, as the rumor further runs that MediaTek is seemingly poised for an initial reveal of this new mobile CPU at Computex in June. The claim is that this piece of silicon will be a major launch for MediaTek, and also Nvidia, of course, with Team Green providing the grunt on the graphics side of the equation.


Analysis: Call to ARMs

These are relatively wispy hints of rumors right now, but obviously MediaTek and Nvidia are big hitters – who have worked together before (in the automotive world) – so it’s certainly possible this proposed SoC is in the works, perhaps using the same process as Apple’s M4 silicon. (TSMC 3nm, or more specifically, its second-gen process, with the M3 built using the original 3nm process).

Get the hottest deals available in your inbox plus news, reviews, opinion, analysis and more from the TechRadar team.

ARM certainly isn’t the only game in town for AI PCs, mind – far from it. Other rivals for Qualcomm’s new Snapdragon X (and this purported MediaTek chip) include traditional (x86) processors from AMD and Intel that pack beefy NPUs that are also ideal for AI PCs. We’re thinking about AMD’s Strix Point and Intel’s Lunar Lake in particular, which are supposedly set to launch later this year.

More competition is always good for the consumer, and more ARM-based options out there should help to drive an important consideration for laptops, too – better battery life. As we’ve seen with another leak earlier today, this is something the Snapdragon X Elite majors in – and there’s no reason why a MediaTek plus Nvidia rival wouldn’t also.

You might also like…

Darren is a freelancer writing news and features for TechRadar (and occasionally T3) across a broad range of computing topics including CPUs, GPUs, various other hardware, VPNs, antivirus and more. He has written about tech for the best part of three decades, and writes books in his spare time (his debut novel – ‘I Know What You Did Last Supper’ – was published by Hachette UK in 2013).

[ For more curated Computing news, check out the main news page here]

The post Nvidia and MediaTek could be cooking up a powerful laptop CPU to blow away Snapdragon X Elite – or even Apple’s M4 first appeared on www.techradar.com

New reasons to get excited everyday.



Get the latest tech news delivered right in your mailbox

You may also like

Subscribe
Notify of
0 Comments
Newest
Oldest Most Voted
Inline Feedbacks
View all comments

More in computing