Perplexity’s Portable Computer Brings Fully Local AI Agent Runtime to NVIDIA RTX and DGX Spark

Perplexity ·

Key Info

Perplexity launched Portable Computer, a fully local version of Perplexity Computer, now available on NVIDIA DGX Spark and Linux systems with NVIDIA RTX GPUs featuring 24GB or more VRAM. The entire runtime—orchestrator LLM, subagent LLM, and agent harness—runs locally with no cloud dependency.

Highlights

  • Portable Computer is a fully local stack: the orchestrator LLM, subagent LLM, and agent harness all run on your own hardware.
  • Available on NVIDIA DGX Spark and Linux PCs with RTX GPUs (24GB+ VRAM), targeting AI users needing on-device agent workloads.
  • No cloud dependency means sensitive data and agent operations can stay on-premises.
Loading...