NVIDIA RTX Spark: Local AI, Unlocked

NVIDIA’s RTX Spark laptops have arrived. With up to 128GB of unified memory and NVIDIA’s AI software stack in a portable Windows PC, the question is no longer just which model to run. It’s how much of your AI you can bring under your own control.

NVIDIA’s Apoorv Chaudhary joins Hannes Rudolph and Patrick Erichsen to unpack the October 16 launch and what it changes for local LLM accessibility, from choosing models that fit in memory to running OpenClaw agents on your own machine.

We’ll get practical: which workloads make sense on a laptop, where the cloud still wins, and what running locally does and doesn’t buy you in privacy, cost, and AI sovereignty.

Bring your questions. This is about making local AI useful to more people, not just building a faster spec sheet.

Explore NVIDIA’s RTX Spark launch

Join the OpenClaw Discord. Next live recording: October 21, 2026 · 11:30 AM PT.