Inferencer v1.5.3 with Xcode Intelligence

Version 1.5.3 is now available for download on the Mac App Store. This update introduces support for agentic code writing and interaction with Xcode Intelligence.

Xcode Intelligence

Xcode 26 allows you to write code directly inside the IDE with AI models. By default it uses Claude or ChatGPT, but it also allows you to select local models either via the internet or locally hosted on your machine. In Inferencer v1.5.3 both integrations are supported, allowing you to let your local AI models write code for you in Xcode either directly hosted on your own machine or on another machine running the Inferencer server with HTTP enabled (SSL support for Xcode coming soon).

Watch the video demo here

P.S. If you find Inferencer useful, please consider leaving a review on the App store, it would be much appreciated.

More improvements

Support for Mixtral has also been added, along with several other improvements. You can submit and vote on features to be added to Inferencer in our public roadmap. In the next update (currently in App Store review) we’ll be bringing support for MiniMax’s latest model (including model streaming support), but more on that later.

Thanks again for your support, and as a reminder, all AI processing is done offline, directly on your device. No telemetry, no background "update" checks.