Nvidia’s RTX Spark N1X laptops ship with up to 128GB memory for local AI
Nvidia’s RTX Spark N1X is the first Windows 11 laptop chip combining an Arm CPU and Blackwell GPU, designed for local AI workloads. Released on 16 October 2026, it powers laptops like the Microsoft Surface Laptop Ultra (€2,899) and ASUS ProArt P16 (€6,699), with memory configurations ranging from 24GB to 128GB. The GPU delivers RTX 4070–5070-level performance, but the CPU lags behind Apple’s M5…
Key points
- RTX Spark N1X ships in laptops since 16 October 2026, with 24–128GB memory (€2,899–€6,699 in Europe)
- 64GB+ memory enables running large open models locally, avoiding cloud dependency and GDPR transfers
- GPU performance matches RTX 4070–5070 laptops, but CPU lags Apple’s M5 Pro/M5 Max by 40–50%
Early benchmarks show the N1X excels in efficiency, drawing 133–144W under load versus 261–305W for gaming laptops with RTX 5090/4090. Memory bandwidth (~300GB/s) limits text-generation speed to ~49 tokens/sec for Llama 3.1 8B, with estimates of ~36 tokens/sec for gpt-oss-120b. Microsoft positions the Surface Laptop Ultra as a ‘builder PC’ for developers and AI creators, while Nvidia emphasizes compatibility with CUDA 13.4 for Windows on Arm. However, IT teams must assess data security, model licensing, and cost savings before adoption.
Model page: RTX Spark N1X →
Nvidia’s RTX Spark laptops bring local AI to Windows, and memory decides who should buy one
i-scoop.eu · 29 October 2026
Loading the full article…
This text was published by i-scoop.eu and written by Tom Cuylaerts. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
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.
More in Hardware & Compute
All →- Piq Energy report shows home batteries may ease data center grid overloads · 1 src
- Wall Street analysts predict Broadcom may outperform Nvidia in AI chip growth · 1 src
- Grace Blackwell’s SkyPilot boosts NVL72 GPU usage by 27% · 1 src
- PCBs and chip substrates may constrain consumer electronics supply, insiders say · 2 src
- Cisco and NVIDIA introduce 400G optics for AI networking with fourfold bandwidth density · 1 src
Comments
via GitHub Discussions