Skip to content
IFAI

Industry

AMD brings dedicated on-chip AI to x86 laptops

Published Reach 44

AMD just unveiled its Ryzen 7040 series mobile processors, marking the first time an x86 chip features a dedicated on-die AI engine called Ryzen AI. Built on the XDNA adaptive architecture, AMD claims it outperforms Apple's M2 in both AI speed and battery efficiency. The first laptops powered by the chip will ship this March.

AMD just dropped a massive mobile processor lineup at CES, cramming 16 desktop-grade cores into high-end laptops and introducing the very first dedicated on-chip AI engine in an x86 processor.

The new Ryzen 7000 mobile lineup is an architectural buffet featuring Zen 4, Zen 3 Plus, Zen 3, and even Zen 2 silicon. But two chip series easily steal the spotlight: the heavy-hitting 7045 series and the AI-equipped 7040 series.

16 full Zen cores meet the Dragon Range

The star of the heavyweight division is the flagship Ryzen 9 7945HX. Built on the Zen 4 architecture, this Dragon Range chip packs 16 cores and 32 threads, clock speeds between 2.2 and 5.4 GHz, 80MB of total cache, and a configurable TDP of 55 to 75 watts.

While Intel claimed top bragging rights with its 24-core Core i9-13980HX, that chip splits duties between eight performance cores and 16 efficiency cores. AMD opted for sheer brute force: all 16 cores on the 7945HX are full-blown Zen 4 cores going full throttle, essentially sandwiching two eight-core desktop dies inside a laptop chassis.

AMD claims this beast delivers a massive 78 percent bump in Cinebench scores over last year's Ryzen 6900HX. You can expect to find it starting in February inside beefy gaming rigs like Alienware's m16 and m18, Asus ROG Strix, and Lenovo's Legion family.

4nm silicon and the debut of Ryzen AI

For mainstream and thin-and-light powerhouses, AMD rolled out the 4nm Zen 4-based 7040 series. Headlined by the Ryzen 9 7940HS and Ryzen 7 7840HS, these chips feature eight cores, 16 threads, boost clocks up to 5.2 GHz, and a 34 to 45-watt power envelope.

The real breakthrough here is silicon-level AI. The 7040 series marks the industry's first mobile x86 processors with dedicated on-chip AI hardware, marketed as Ryzen AI. Powered by AMD's XDNA adaptive architecture, it takes over routine AI workloads like real-time background blurring, audio cleanup, and video enhancements.

AMD claims these chips can beat Apple's M2 in both raw performance and energy efficiency, handle up to 30 hours of battery life, and outmuscle the M1 Pro in select scenarios. As AMD CEO Lisa Su declared during her keynote, AI is the defining megatrend in tech. Laptops running 7040-series chips will start shipping in March.

Why it matters

We think this is the official start of the on-device AI race for x86 laptops. For the last couple of years, Apple has enjoyed an undisputed lead in energy-efficient local machine learning tasks thanks to its Neural Engine, leaving Windows machines to either burn battery on the CPU or spin up an power-hungry discrete GPU. Putting dedicated XDNA silicon straight onto the die finally gives Windows laptops a chance to match Apple's battery-friendly background tasks.

That said, buyers should temper their excitement before rushing out to buy a 7040 machine on day one for AI alone. Hardware is only as good as the software driving it. Outside of basic Windows webcam tricks, third-party software support for AMD's AI block remains unproven. If you are shopping purely for everyday performance and battery life, the 4nm jump looks promising, but the AI promise needs real-world testing once devices ship in March.

Strategically, AMD played this hand brilliantly. By going all-in on 16 full-power cores at the top end, it offers heavy creators and gamers a pure performance alternative to Intel's hybrid architecture. And by beating Intel to the punch with dedicated x86 AI silicon, AMD successfully shifts the narrative from pure clock speeds to everyday intelligent efficiency.

Sources (2)

  1. [1]
    androidauthority.com(opens in a new tab)Originalandroidauthority.com
  2. [2]

Similar events

Past happenings like this one, for context.

Best of AI, daily