IFA 2026 in Berlin brought the first hands-on look at the Nvidia RTX Spark superchip inside a laptop, alongside new mini desktops designed for local AI workloads.
Three months ago, Nvidia revealed the chip and a few future devices. Now, actual hardware is available to examine. Demand for running agentic AI workflows like OpenClaw locally is rising, and these new machines appear built specifically to support that need.
Lenovo alternatives to the MacBook Pro
The laptop on display is the Lenovo Yoga 9n 2-in-1. It is a 16-inch device with a 360-degree hinge. The build quality looks premium, aiming to compete directly with the MacBook Pro. The OLED touch screen has a 2880 x 1800 resolution and a 120-Hz refresh rate. The chassis features rounded metallic edges and very thin display bezels. High-end features not typically seen include a six-speaker sound system and a 9.2-megapixel webcam.
The key detail is the thickness: 0.69 inches. That is just 0.03 inches thicker than the 16-inch MacBook Pro. This is possible because of Nvidia’s Arm-based chip under the hood. It combines a Grace CPU with up to 20 cores and a Blackwell RTX GPU with up to 6,144 cores. The CPU, GPU, and memory are packaged into a single system-on-a-chip (SoC). This sharing of components is more similar to Apple silicon than a conventional Windows laptop.
Based purely on core count, the integrated GPU capability of this chip would theoretically place it between an RTX 5070 Ti and an RTX 5080 found in current laptops. Those specs also indicate that lower-powered configurations will be sold, though the performance range is unknown. There were no battery-life claims. Presumably, using an Arm-based SoC rather than a discrete GPU offers greater efficiency and better battery life.
I do not prefer large laptops with 2-in-1 capabilities and number pads. I am more interested in the Yoga Pro 9n, a 15-inch model. It was not available to see in person. It shares rounded edges, a higher-resolution webcam, and a large haptic touchpad with the 16-inch model. The screen is 15 inches with a 2560 x 1600 resolution. It is thinner at 0.66 inches at its thinnest point. A unique feature is the Force Pad touchpad, which lets you use a stylus, such as the Yoga Pen Gen 2, to write or draw directly on the surface.
The Yoga 9n 2-in-1 can only be configured with up to 64 GB of memory. This is less than I expected for AI-focused PCs. The Yoga Pro 9n is the “Pro” model because it offers configuration options up to 128 GB of memory. Otherwise, the performance seems the same.
The Lenovo device is just one of a new line of RTX Spark-powered laptops coming this fall. This includes the Dell XPS 16, Asus ProArt P16, and Microsoft Surface Laptop Ultra. These larger laptops seem focused on the creator and AI enthusiast demographic. Only one 14-inch model has been announced so far: the HP OmniBook X 14.
AI Boxes
The point of these new PCs is to offer hardware that can run on-device AI models locally. This means less dependence on the cloud and more ability to run full agentic AI workflows without worrying about privacy. This is crucial when an AI model handles sensitive personal data like financial information, email accounts, or anything else you feel comfortable providing.
Acer announced its own mini PC solution, the Acer SFF RTX Spark. It follows up on Asus’ ProArt Mini PC shown off earlier this summer. Both are around the same size as the Mac Mini. They offer a petaflop of AI performance, up to 128 GB of memory, and the same RTX Spark superchip at their core. These mini PCs are interesting, coming just a week after the announcement of Apple’s M6 Mac mini and M5 Ultra Mac Studio. These small, efficient desktop computers are going to play an important role in the adoption of local AI.
Nvidia is not the only player here. Lenovo announced an AMD-powered ThinkCentre X Ultra. It puts 128 GB of memory at the disposal of agentic AI models alongside AMD’s Ryzen Max+ Pro 495 chip. This is another popular chip being used for local AI, such as on the Framework Desktop. You can even buy the AMD Developer Kit with 128 GB of RAM right now. The expected starting price of the ThinkCentre X Ultra is $3,699. That is the base model, not the maxed-out, 128-GB version.
Price remains the most crucial missing element. RAM has never been more expensive or more necessary. I would not expect any RTX Spark systems to be cheap. The most affordable MacBook Pro, aside from the M5 base model, is $2,349. That gets you the M5 Pro and only 24 GB of RAM. For a 128-GB MacBook Pro, you are currently looking at $6,139.
What it means
These devices signal a shift toward local processing for sensitive tasks. Users can run AI models on their own hardware without sending data to the cloud. The high cost of memory means these machines will remain expensive for the foreseeable future.
