NVIDIA Announces RTX Spark Platform Featuring Up to 128GB Unified Memory for Local AI Execution
NVIDIA has revealed its RTX Spark superchip platform for laptops, offering up to 128GB of unified memory and 1 petaflop of AI compute. The platform focuses on running local LLMs and AI agent frameworks directly on consumer hardware without relying on cloud services.
NVIDIA has announced laptops powered by its next-generation RTX Spark platform, scheduled for release on October 16, 2026. The new superchip combines up to 128GB of unified memory with 1 petaflop of local AI computing performance on a single die. Designed as a personal AI supercomputer, the hardware provides full access to the local NVIDIA RTX and CUDA software stack for advanced development workloads.
Primary source
Open NVIDIA ↗This article summarizes the source. Check the original for full details and conditions.
