Inferencer v1.7.2 with VS Code

In version 1.7.2 of Inferencer, support for running local models directly through VS Code is now supported.

VS Code

The tools supported are Microsoft AI Toolkit and Continue.dev, with GitHub CoPilot coming in v1.7.3. The OpenAI and Ollama compatibility APIs have been upgraded to support these tools and expanded to support distributed and remote compute. To set up, just launch servers on both your computers, join one to the other and when connecting via VS Code, remote and distributed models will be included.

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

More Improvements

Also in this release you will find bug fixes to distributed compute and model streaming.

As always, if you have any features or suggestions you’re more than welcome to add them to our public roadmap.

What about DeepSeek V3.2?

Also if you want a sneak peek at how the latest version of DeepSeek runs in the next version, watch this video.

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