Perplexity has released Portable Computer, a local-first build of its agentic Computer platform that runs the agent harness, orchestrator, planner, tool router and post-trained models directly on NVIDIA DGX Spark. The local model, inference engine, tool sandbox and app connectors ship as one packaged system, every task begins on the device, and work handled by local models carries no per-token charge. When a step needs the live web or frontier reasoning, the orchestrator stops and asks before sending that single step to one of 15+ cloud models.
Is it deployable?
Yes, with a hard hardware gate. This is shipping software, not a preview binary, but it needs a GB10-class box or an RTX GPU with 24 GB of VRAM under the desk.
Company level: Enterprises and mid-market teams that already own NVIDIA workstations, plus well-funded AI-native startups. Not viable for general SMBs — the machine is the price of entry.
Industries: Finance, legal, healthcare, government and defense, and IP-heavy engineering — anywhere data residency or contractual confidentiality blocks cloud inference.
