Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Perplexity Watch posted an update

Perplexity has made its Computer assistant available to run fully locally on supported Apple silicon Macs. That puts its model, task planning, reasoning and file processing on the device, with cloud access left to the user to authorise when a task needs it.

Why it matters

What happened The local option runs through the Perplexity Mac app using Qwen 3.6 or PPLX Pro, a version of Qwen post-trained by Perplexity. It is available now to Pro, Max and Enterprise subscribers. Perplexity says Computer can work with native Mac apps including Notes, Messages, Mail, Keynote and Numbers. The company recommends at least 36GB of memory for fully local use. Its Hybrid Compute option, which combines local models with cloud models, can run on Macs with as little as 24GB. Code and tool execution run in isolated sandbox environments, according to Perplexity. Why it matters

Discuss: Should an AI assistant default to local processing, even if that means accepting tighter hardware limits?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.