Perplexity launches Portable Computer, an AI agent that runs entirely on your own machine

Key points

• Perplexity launched Portable Computer on Monday in partnership with Nvidia, bringing its AI agent software to local hardware for the first time.
• The product runs on Nvidia DGX Spark desktop machines and Linux PCs with compatible Nvidia RTX graphics cards, with Windows support coming in September 2025.
• All processing happens on the user's own device by default, meaning no cloud fees per task and no automatic upload of sensitive files.
• On Perplexity's own 53-task benchmark, its co-designed agent scored 85.4% accuracy versus 77.6% for the nearest open-source rival.
• The minimum hardware requirement is an Nvidia GeForce RTX 3090 graphics card with at least 24 GB of video memory.

Perplexity, the AI search company, has released a product it calls Portable Computer: a version of its "Computer" agent platform that runs entirely on hardware you already own. An AI agent, for context, is software that can carry out multi-step tasks on its own, such as reading a folder of documents, spotting problems, and writing a summary report. Until now, running that kind of extended task meant sending your files to a remote server and paying for every step.

Portable Computer changes both of those things.

What does it actually do?

The software packages everything an AI agent needs into a single download: the AI model itself, the tools it uses, and the logic that keeps it on track. You install it, point it at your documents, and it works.

At a press briefing Monday, Perplexity's vice president of engineering, Nate, showed the agent reviewing a folder of 1099 tax forms and investment statements on a local machine. The agent flagged cases where a hypothetical investor was paying unnecessary fees. The credit counter on screen stayed at zero throughout because nothing left the device.

A second demo showed the hybrid angle. An agent analysed a spreadsheet of sales funnel data locally, then pushed the finished report to a Slack channel. Local-first does not mean cut off from everything else. The system also connects to Google Drive, Gmail, and GitHub, and can hand a task off to a more powerful cloud model if the local one runs into a problem it cannot solve, but only after asking permission first.

Why does running it locally matter?

Privacy is the obvious reason. Financial records, medical notes, and internal business data are exactly the kind of material many people are uneasy uploading to a third-party server. Here, those files never leave your desk.

Cost is the other reason, and it becomes significant fast. A simple chat message takes a second. An agent that spends two hours combing through hundreds of documents, checking its own work, and producing a report can generate an enormous number of individual computation steps, each of which normally carries a small fee on a cloud service. On your own machine, that marginal cost drops to near zero.

"With agents, you want these agents always on if you can," said Nader, Nvidia's director of developer technology, at the briefing. "You were not metered by the token. You were not paying for the token. So it's really killer for agents."

How does it perform against the competition?

Perplexity published a research paper alongside the launch arguing that small local AI models need a custom-built harness, the scaffolding of instructions and tools around the model, rather than the general-purpose frameworks designed for much larger cloud models. The company says it co-designed its harness and model together, and its numbers reflect that.

These figures come from Perplexity's own internal benchmark of 53 tasks, which the company says it will open-source. Independent verification does not yet exist, so treat the gaps as directionally interesting rather than settled fact.

At launch, users can choose between Qwen 3.8 27B, an open-source model from Alibaba's research lab, and PPLX 27B, Perplexity's own fine-tuned version, with a third option from Nvidia coming soon.

Who can use it right now?

Portable Computer is available today on Linux for subscribers on Perplexity's Pro, Max, Enterprise Pro, and Enterprise Max plans. Windows support follows in September. The minimum requirement is an Nvidia RTX graphics card with 24 GB of video memory, roughly a GeForce RTX 3090 or newer. That is a high bar for a home PC but standard on many professional workstations.

First reported by VentureBeat, the launch marks one of the more serious attempts to move genuine AI workload off remote servers and back onto local machines, at a moment when both the models and the hardware have grown capable enough to make it practical.