Perplexity Computer Runs Fully Local on Apple Silicon Macs

Perplexity Computer now runs fully local on supported Apple silicon Macs, with both the model and agent executing on-device without cloud inference. Local tasks use PPLX Pro, a post-trained version of Qwen 3.8, and do not consume Computer credits. The feature is available to Pro, Max, and Enterprise subscribers, with 36 GB of unified memory recommended.
Event version 1.
Key insights
On-device model and agent
Perplexity Computer can run fully local on a Mac, with both the model and the agent executing on the device. Tasks run without sending sensitive data to the cloud.
PPLX Pro local model
Local tasks use PPLX Pro, a post-trained version of Qwen 3.8. Local tasks do not consume Computer credits.
Hybrid mode for complex work
Hybrid mode can split a task between cloud models and a local model on the Mac. This keeps sensitive data private for more complex work.
Subscriber and hardware requirements
The feature is available to Pro, Max, and Enterprise subscribers on supported Apple silicon Macs. 36 GB of unified memory is recommended.