GPU Infrastructure Agent runtime infrastructure Model serving

NVIDIA RTX Spark

A 128GB unified-memory AI PC platform with 1 PFLOP of FP4 compute

NVIDIA RTX Spark is presented as an AI PC platform built around 128GB of unified memory and approximately 1 PFLOP of FP4 AI compute, intended for local inference and fine-tuning on Windows on Arm systems.

Recent stories

1 linked story

releasePRIMARY2026-06-01

Microsoft and NVIDIA launch RTX Spark PCs with 128GB unified memory and 1 PFLOP FP4

Microsoft and NVIDIA unveiled RTX Spark systems, including Surface Laptop Ultra and DGX-class Windows hardware, with 128GB unified memory and 1 PFLOP FP4 local AI. Day-one support from Hermes Agent, vLLM, Ollama, and Unsloth makes the launch useful for local inference and fine-tuning, not just a PC refresh.