Introduction

For years, a Surface laptop meant one thing: a beautifully built Windows machine for people who answer emails, write documents, and maybe edit a photo or two. Gaming and heavy GPU work were always somebody else's job. The Surface Laptop Ultra intends to change that. It's the first Surface with NVIDIA inside, and not just a discrete graphics card bolted next to an Intel chip, but NVIDIA's brand-new RTX Spark platform, where the Arm CPU and the Blackwell GPU live in one package and share a single pool of memory.



Since this is the first RTX Spark laptop we've tested, the next two pages cover the platform itself, with a look at the architecture and NVIDIA's push for local AI agents. The short version: the NVIDIA N1X processor combines a 20-core CPU with Arm-based CPU cores with a Blackwell GPU that has 6,144 CUDA cores, and both are connected to a fast, shared, LPDDR5X memory pool that goes up to 128 GB. That memory pool is what makes this so special. A typical NVIDIA laptop GPU is stuck with 8 to 24 GB of its own dedicated VRAM, while here, the CPU and GPU share common memory. That's what lets this laptop run local AI models and agents that simply won't fit on a regular gaming notebook.

Today, I'm checking out the Microsoft Surface Laptop Ultra with the full NVIDIA N1X chip. Microsoft sells two versions: the 18-core models come with a 5,120-core GPU and 24 or 32 GB of memory, while the 20-core models get the full 6,144-core GPU and 32, 48, 64, or 128 GB. Our unit sits at the very top of the range, with 128 GB of unified memory and a 1 TB PCIe 5.0 SSD. The NVIDIA App lets you adjust how much of that memory goes to the GPU. By default, it is split evenly, with 64 GB for the GPU and 64 GB for Windows.

The display on the Surface Laptop Ultra is a 15-inch PixelSense Ultra panel with a 3:2 aspect ratio, a resolution of 3270×2180, a 120 Hz refresh rate, and mini-LED backlighting. Microsoft rates it at 1,000 nits in SDR and up to 2,000 nits with HDR content. It's also a touchscreen.

Port-wise, you get three 40 Gbps USB4 Type-C ports (one doubles as a magnetic charging port), a 5 Gbps USB-A port, HDMI 2.1b, a full-size SD card reader, and a headphone jack. The battery is a 92 Wh unit, and the whole laptop weighs 2 kg while measuring 17.99 mm thick, without the feet.

As you can imagine, this kind of hardware doesn't come cheap. The Surface Laptop Ultra starts at $2,600 in the US, while our top-of-the-line 128 GB configuration will set you back $5,900. So, the questions are pretty clear. Is NVIDIA's RTX Spark a real alternative to a gaming laptop with a dedicated GPU? How does the Arm CPU handle everyday Windows software? Most importantly, is local AI a good enough reason to spend this kind of money? Let's find out.

Specifications

NVIDIA RTX Spark Architecture

Before we get to the laptop itself, let's take a quick look under the hood. The heart of the Surface Laptop Ultra is the N1X, which NVIDIA calls a superchip. In practice, that's two pieces of silicon (tiles) sitting side by side in one package and talking over NVLink C2C, a chip-to-chip link rated at 600 GB/s with bidirectional coherency. Both tiles are made on TSMC's 3 nm process.


You can make out the two tiles here, each with NVIDIA's own markings. Look closely near the arrows; you can see the split where they sit together.


The first tile is the Blackwell GPU. It packs 6,144 CUDA cores across 48 streaming multiprocessors, 5th-generation Tensor cores good for 1 PFLOP of NVFP4 AI performance, 4th-generation RT cores, 24 MB of L2 cache, and the video engine with 4:2:2 encoding and decoding plus AV1 UHQ. In other words, it's a proper RTX 50-series class GPU, with full support for CUDA, DLSS 5, Multi Frame Generation, and Ray Reconstruction. No compromises on the software side.


The second tile was built together with MediaTek, and it holds everything else: the 20-core Grace CPU, the memory controller, the NPU, the display outputs, and the I/O, including PCIe Gen 5, USB4, and Wi-Fi 7. One interesting detail here is that the memory controllers sit on the CPU tile. So, every byte the GPU pulls out of the shared memory has to cross the C2C link first. If the 600 GB/s figure is the sum of both directions, each direction gets about 300 GB/s, which matches the peak bandwidth of the memory. That's my reading, not NVIDIA's, but it looks like the link was sized to carry exactly what the memory can deliver.

Two Versions of N1X

RTX Spark comes in two flavors, and Microsoft offers both in the Surface Laptop Ultra.


The bigger chip gets 11% more CPU cores and exactly 20% more GPU cores, but both versions share the same memory interface. Keep in mind that the 45–80 W range covers the CPU and the GPU together, so it can't be compared directly with the TGP of a discrete laptop GPU, which only covers the graphics card. NVIDIA's own lineup chart ties the smaller chip to the 24 and 32 GB configurations, meant for gaming, content creation, and agents that rely on cloud models. The 20-core version covers everything, including local AI models, large 3D scenes, and video generation.

The CPU Cores

This is the die shot of the 20-core Arm-based CPU. Unlike Qualcomm's Snapdragon X chips with their custom Oryon cores, NVIDIA uses existing Arm CPU IP: the Cortex-X925 for performance and the Cortex-A725 for efficiency. Both are ARMv9.2 cores without SMT, so 20 cores also means 20 threads. The X925 was originally meant for the flagship phones of 2025, where it runs at much lower clocks. Here, it gets proper laptop cooling and clocks reach 4.0 GHz. And as you'll see on the clocks page, the Surface Laptop Ultra keeps them there under full load. The A725 isn't a tiny background core either, Arm classifies it as "Premium Efficiency," which can be translated as a medium core. It runs at up to 2.8 GHz and does real work in multithreaded loads. The two clusters get 16 MB of L3 cache each.

This design approach is very different from Intel's approach. Panther Lake leans on up to eight small Darkmont E-cores, paired with four large Cougar Cove P-Cores, and four more Darkmont Low-Power-Efficient cores, while NVIDIA goes half-and-half, which gives N1X a much bigger pool of large cores.

Unified Memory

NVIDIA N1X uses LPDDR5X on a 256-bit, 16-channel interface rated at up to 9,400 MT/s. That works out to roughly 300 GB/s of peak bandwidth, shared by the CPU and the GPU. That's ahead of AMD's Ryzen AI Max+ 395 and Qualcomm's Snapdragon X2 Elite, roughly level with Apple's M5 Pro, and about half of what the M5 Max offers.
Bandwidth decides how fast a language model writes text, while capacity decides whether a model fits at all. NVIDIA's favorite chart shows exactly that. Jobs like large AI agents, video generation, and huge render scenes need tons of memory, and a laptop with a regular discrete GPU simply can't reach them at any power level. RTX Spark can, at just 45–80 W.


Microsoft also did its part. Windows now gives the GPU a larger, more adaptive share of system memory and supports larger memory pages for demanding workloads. If you'd rather decide yourself, the NVIDIA App has a GPU memory allocation slider under 'System,' then 'Advanced.' Just keep in mind that every change requires a restart.