Perplexity launches privacy-minded ‘hybrid compute’ AI feature for Mac

Perplexity launched Hybrid Compute for its Mac app, a privacy-minded feature that splits AI tasks between cloud models and a local model on the Mac, with an on-device PII classifier that swaps names, addresses, and account numbers for stand-ins before sending data to the cloud. The feature requires Apple silicon with macOS 15+ and 24GB unified memory minimum (32GB recommended), and uses the open-sourced PPLX Qwen 3.8 27B model, which can be downloaded in one click. Perplexity first announced the split-task capability in June and has open-sourced the PII classifier trained with its Secure Intelligence Institute.

Aside from being featured by Apple in the M6 Mac mini https://amzn.to/4gNHAip launch, Perplexity has been relatively quiet on the Mac front this summer. That changes today with hybrid compute for Mac. Perplexity first announced https://9to5mac.com/2026/06/02/perplexity-computer-adding-ability-to-split-tasks-between-local-and-cloud-models/ work on splitting AI tasks between local and cloud models in June. Today, Hybrid Compute is launching as part of Perplexity’s Mac app. “Computer now splits a task between cloud models and a local model on your Mac,” the company says. “Computer starts each task in the cloud. Trigger one from your iPhone, and your Mac accesses your files and runs sensitive steps locally.” Perplexity’s website explains how the new feature works: Our on-device PII classifier reads each task on the Mac before it is sent. Names, addresses, and account numbers are swapped for stand-ins, then restored when the answer returns. We’ve open-sourced the on-device PII classifier, trained in collaboration with Perplexity’s Secure Intelligence Institute . Macs with 8GB and 16GB RAM won’t be able to run hybrid compute, according to Perplexity. 24GB memory is the minimum, and 32GB is recommended as the floor: Hybrid Compute runs on Apple silicon, macOS 15+— 24 GB unified memory minimum, 32 GB for best results. Set up the local model once: download PPLX Qwen 3.8 27B in one click. No Ollama or manual runtime setup. Work it handles uses no cloud credits. No API key. MacStories also has coverage https://www.macstories.net/news/perplexity-introduces-hybrid-compute-to-keep-sensitive-data-local/ of the new Perplexity feature today. You can learn more from Perplexity’s announcement page here https://www.perplexity.ai/hub/products/hybrid-compute . Hybrid compute is just the latest AI tool from Perplexity that takes advantage of the power of the Mac. In May, the company overhauled its Mac app https://9to5mac.com/2026/05/07/perplexity-ai-app-introduces-all-new-native-mac-experience-for-personal-computer/ with a whole new version. Apple specifically cites https://www.apple.com/mac-mini/ Perplexity Personal Computer as a productivity use case for the new M6 Mac mini https://amzn.to/4gNHAip as well. Do more with your Apple products Apple AirTag 2 | Add Find My tracking to keys, bags, bikes, more https://amzn.to/4vjNWN1 AirPods 4 | Apple’s newest wireless headphones https://amzn.to/43ndewV AirPods Pro 3 | Apple’s best wireless headphones https://amzn.to/4ut3FYp Beats USB-A to USB-C Cable | The official CarPlay cable https://amzn.to/4mpKs7K FTC: We use income earning auto affiliate links. More. https://9to5mac.com/about/ affiliate our homepage http://9to5mac.com/ for all the latest news, and follow 9to5Mac on exclusive stories https://9to5mac.com/feature/exclusive/ , reviews https://9to5mac.com/guides/review/ , how-tos https://9to5mac.com/guides/how-to/ , and subscribe to our YouTube channel https://www.youtube.com/9to5mac