The whole agent runtime moves on-device, with gated cloud escalation
- Source
- x.com
- Date
Today we’re launching Portable Computer on @NVIDIA DGX Spark. Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness all run on your local hardware. No cloud dependency.
When a task needs frontier reasoning, the orchestrator asks for approval before routing it to a frontier model in the cloud. It's user-gated, PII-flagged, and text guidance only. Your sensitive documents stay on your device.
Portable Computer runs a post-trained and locally installed PPLX 27B model. Qwen 3.8 27B is also available, with support for NVIDIA Nemotron 3.5 Lightning coming soon.
Portable Computer is available today for all Perplexity Pro and Max subscribers with an @NVIDIA DGX Spark. Get started: https://t.co/9iGbVqhZor
Context
Perplexity's Portable Computer moves the coordinating model, delegated models and software that runs their work onto local hardware. Its August 25 launch targeted Pro and Max subscribers with an NVIDIA DGX Spark. When a task needs stronger cloud reasoning, the company says the coordinator asks for approval and uses the remote model for text guidance. The arrangement makes local execution the starting point while retaining an explicit route to outside assistance. The launch thread describes that boundary.
- multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Checking sign-in…
Loading comments…