Perplexity enables fully local AI workflows on Apple Silicon Macs
Perplexity has expanded its Computer app so users can run its entire AI agent experience, including the orchestrator and harness, locally on an Apple Silicon Mac with at least 36GB of RAM. Users can pick between two local models, Qwen 3.6 or Perplexity's own fine-tuned PPLX Pro, and still call on over 15 frontier models when needed. The feature is rolling out now to Perplexity Pro, Max and Enterprise subscribers via the Mac app.
GoKawiil's interpretation of the reporting above, not reported fact.
By letting tasks run entirely on-device, Perplexity is positioning local compute as a way to cut cloud costs and keep sensitive data like emails and notes off external servers, according to the company. This follows its earlier Hybrid Compute feature and suggests a broader push toward blending local and cloud AI as on-device hardware grows more capable. It could also pressure rivals to offer similar privacy- and cost-conscious local processing options.
- Perplexity Computer can now run fully locally on Apple Silicon Macs with 36GB+ RAM.
- Users choose between Qwen 3.6 or Perplexity's custom PPLX Pro model, with access to 15+ cloud models when desired.
- Feature is live today for Perplexity Pro, Max and Enterprise subscribers via the Mac app.
Apple MacBook Pro M4 Pro — Since Perplexity's fully local Computer mode requires an Apple Silicon Mac with at least 36GB of RAM, a MacBook Pro with the M4 Pro chip is a great fit for running AI workflows entirely on-device. It gives you the horsepower and memory headroom to handle demanding local orchestration tasks while keeping your Mail and Notes data private and off the cloud.
See Apple MacBook Pro M4 Pro on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: engadget.com — Igor Bonifacic, 2026-10-20
Published there as: “Perplexity makes it easier to run AI workflows entirely on your own Mac”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.