Microsoft has just announced the Surface Laptop Ultra, powered by Nvidia’s latest RTX Spark Superchip for laptops and desktop PCs, at Computex 2026. Claimed to be the most powerful Surface laptop device yet, the new Surface Laptop Ultra is essentially Microsoft’s answer to the current-gen MacBook Pro. The company has positioned the notebook primarily for AI development but also for creators and developers who seek powerful performance in a portable package.
Made in collaboration with Nvidia, the Surface Laptop Ultra will be one of the first devices featuring the RTX Spark Superchip. Nvidia’s new Windows on Arm platform is claimed to be more powerful and capable than any other on the market featuring 20 Arm CPU cores, a Blackwell GPU with 6144 CUDA cores, 128GB of unified LPDDR5X RAM, and up to 300 GB/s of memory bandwidth. The CPU and GPU are interconnected using NVLink C2C, while the large pool of unified memory can be dynamically allocated between the CPU and GPU. Offering up to 1 petaflop of AI compute, the RTX Spark is capable of running up to 120B parameter models locally.
Image 1 of 2
As for the device itself, the new Surface Laptop Ultra will feature a 15-inch mini-LED PixelSense Ultra display with a resolution of 2880 x 1920, offering 262 pixels per inch. Microsoft claims that it can reach up to 2,000 nits of peak HDR brightness, which should be excellent for creators on the go. It also features a large haptic touchpad along with a good selection of ports, including HDMI, USB-C, USB-A, SD card reader, and a headphone jack. Weighing under just 4.5 pounds, it will be available in Platinum (silver) and Nightfall (black) color options. Microsoft claims all-day battery life on the laptop and an optimized internal layout with dual-fans to maintain proper thermals for sustained performance.
The new Microsoft Surface Laptop Ultra is expected to arrive later this year, with final pricing and availability to be announced closer to launch. With the ongoing RAM-apocalypse, it seems like a smart move by Microsoft to adopt Nvidia’s new Arm platform with unified memory. Beyond reducing the need for large pools of dedicated system and graphics memory, the architecture should also help improve efficiency and enable larger AI models to run locally without relying heavily on cloud resources. If Nvidia’s performance claims hold up in real-world workloads, the Surface Laptop Ultra could emerge as one of the most compelling Windows alternatives to Apple’s MacBook Pro for AI developers, content creators, and power users alike.
