DigestAI news desk

Cut through the AI noise.

Hardware & Compute16 min read

Microsoft Surface Laptop Ultra reviewed as first RTX Spark flagship with Nvidia N1X chip

PCMag reviewed the Microsoft Surface Laptop Ultra, the first laptop built on Nvidia's new RTX Spark platform. The flagship starts at $2,599.99 with an 18-core N1X chip, 24GB unified memory, and 512GB SSD; the tested unit has a 20-core N1X, 64GB memory, 1TB SSD, and costs $4,299.99. A top configuration with 128GB memory reaches $5,899.99.

1 source

Key points

  • Surface Laptop Ultra starts at $2,599.99 with Nvidia RTX Spark N1X chip and unified memory
  • Apple MacBook Pro 16-inch M5 Max leads in CPU, graphics, battery, and AI generation speed

The N1X system-on-chip combines Grace CPU cores and Blackwell GPU cores with unified memory shared between them, similar to Apple Silicon. In benchmarks, the Surface Ultra scored 1,649 in Cinebench 2024 multi-core, transcoded 4K video in 2 minutes 29 seconds, and hit just above 19,000 in Geekbench 6.3. It led RTX Spark peers in 3DMark graphics tests but trailed the Apple MacBook Pro 16-inch (M5 Max) across CPU, graphics, and battery life (15 hours 40 minutes vs. over 27 hours).

AI testing placed the 64GB unit in PCMag's Class 2 tier. Using Llama 3.1 8B, it achieved 0.35-second time-to-first-token and edged the Asus ProArt P16 on tokens per second. With Phi 4 Reasoning 14B, it reached 31.1 tokens per second, again slightly ahead of the ProArt. The MacBook Pro nearly doubled that rate. The review notes the RTX Spark platform is early and gaming on Arm remains limited.

Model page: RTX Spark N1X →

The story so far

3 episodes →
  1. Microsoft Surface Laptop Ultra reviewed as first RTX Spark flagship with Nvidia N1X chipthis story
Full story from tech.yahoo.com · by Brian Westover · via Search: MicrosoftOpen source ↗

Microsoft Surface Laptop Ultra Review: With This Slick Flagship, the RTX Spark Era Is Just Getting Started

tech.yahoo.com · 4 November 2026

Loading the full article…

This text was published by tech.yahoo.com and written by Brian Westover. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Hardware & Compute

All →

Related stories