DigestAI news desk

Cut through the AI noise.

Hardware & Compute1 min read

Microsoft unveils Surface Laptop Ultra with RTX Spark SoC for AI workloads

The laptop, starting at $2,599, integrates Nvidia’s RTX Spark SoC for AI and gaming tasks. It features either a 5120-core or 6144-core Blackwell GPU and up to 128GB of LPDDR5x unified memory, shipping on October 16. The device highlights unified memory allocation to handle modern gaming and local AI development without traditional VRAM limits, as demonstrated by running Gears of War: E-Day…

1 source

Key points

  • Surface Laptop Ultra starts at $2,599 with RTX Spark SoC for AI and gaming, shipping October 16
  • Dev Box costs $5,999, offers 128GB memory and one petaflop AI compute for developers
  • Unified memory allocation enables AAA gaming and local AI workloads without VRAM limits

Microsoft also introduced the $5,999 Surface RTX Spark Dev Box, co-announced with Nvidia CEO Jensen Huang and Microsoft CEO Satya Nadela. The box is designed for frontier developers, shipping with a custom Windows 11 build optimized for AI workloads. It includes 128GB of unified memory and an RTX GPU, delivering one petaflop of AI compute performance, according to Microsoft.

The story so far

3 episodes →
  1. Microsoft unveils Surface Laptop Ultra with RTX Spark SoC for AI workloadsthis story
Full story from Ars Technica AI · by Nick IndgeOpen source ↗

Microsoft event debuts new AI-friendly hardware and Windows changes

Ars Technica AI · 8 October 2026

Loading the full article…

This text was published by Ars Technica AI and written by Nick Indge. 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