Perplexity launches Portable Computer for local-first AI on NVIDIA DGX Spark
Perplexity Portable Computer
Perplexity has introduced Portable Computer, a version of its AI agent that runs entirely on a local machine, built with NVIDIA. Available on the NVIDIA DGX Spark and soon on RTX GPU PCs, it lets users analyze private data, synthesize files, and run complex workflows on-device without consuming credits. Sensitive data stays local, while authorized tasks can escalate to the cloud for advanced research. The system uses Qwen 3.8 27B or PPLX 27B models, with NVIDIA Nemotron 3.5 Lightning coming soon. It includes local search, dictation, and app connectors for Google Drive, Gmail, Slack, and GitHub.
People no longer have to ration what they use intelligence for.
- hmokiguess
Who is this aimed at, I question that, it has the mixture of someone technical enough to invest in a DGX Spark and to know about Open Weight self-hostable models, but then tries to offer a sort of subscription package "we will do it for you" -- does this consumer even exist? I feel like if I owned a DGX Spark I would just build this orchestrator myself, or use some open source stuff out there, definitely would not buy into a subscription from them for this
- jazzpush2
Just let Perplexity die already.
- nycdatasci
To clear up the confusion on naming: "Computer" is their cloud-hosted, multi-model harness/router. "Portable Computer" allows you to run the harness locally. You have you bring your own DGX Spark.
It's unclear why this is tied to the Spark. Shouldn't we be able to run this on any system that is capable of running local inference?