LM Studio’s Locally app is being updated today with Link, a feature that lets users talk to LLMs running on their Macs right from their iPhones. Here are the details.
LM Link lets you talk to local LLMs on your Mac #
LM Studio is my go-to Mac app for running LLMs locally. Its model search feature is fantastic for finding the AI models best suited to my Mac’s hardware, helping me avoid models that might be too demanding for my 16GB M2 Pro MacBook Pro. And once the model is installed, LM Studio’s tools for adjusting its performance to my needs are by far the easiest and most complete I’ve used.
Today, LM Studio is updating its Mac app, and the Locally AI iOS app (which the company acquired earlier this year), with a new feature called LM Link. It establishes a secure connection between the iPhone and the Mac, allowing users to interact with the local models running on their Macs right from their iPhones.
Using LM Link requires you to create an LM Studio account and sign in to it on both devices. Once that’s done and you activate LM Link, it establishes an end-to-end encrypted connection that keeps data flowing privately and securely. This means you can still rely on the privacy aspect of running and processing an LLM locally on your Mac, even though you’re sending data back and forth as you use it from your iPhone.
From LM Studio:
Your devices, linked together #
End-to-end encrypted networking. All data and communication between devices remain entirely private and secure. Your devices are never exposed to the public internet, because LM Link runs on top of custom Tailscale mesh VPNs.
On the Tailscale collaboration, LM Studio says that “LM Link is an entirely separate and self-contained use of Tailscale VPN primitives,” which means that LM Link will not interfere with an existing Tailscale VPN, if that’s the case.
LM Link works with any model users have installed on their Macs (including the built-in Apple Intelligence foundation model), with performance depending on the Mac’s hardware, as with any local model.
Finally, LM Studio says that during the Preview period, LM Link will be free. After that, in addition to a free plan, the company will release paid plans, with details on that still to come.
9to5Mac’s take #
I have used LM Link for a few days, and the experience has been great. I rely on local LLMs for specific parts of my workflow, and it has been a great addition to have the option to do that part of the work on my iPhone when on the go.
If you notice that the connection gets dropped too quickly after the iPhone app spends a few moments in the background (for instance, when you leave Locally AI’s chat to locate some documents, or do a quick web search, then hop back on Locally AI), I’ve noticed that too. The developers tell me this is a byproduct of how the secure connection is established. Still, they are working to improve latency for a faster reconnection and keep the connection alive longer.
LM Link is a great feature, and if you rely on models that run locally on your Mac, you should try it. The same goes if you’ve been thinking about giving local models a try. There has never been a best time for that either, particularly after Google released a 12-billion-parameter version of Gemma 4 yesterday, designed to run on Macs with 16GB of memory or more.
You can learn more about LM Link here.
Worth checking out on Amazon
Geoffrey Cain – ‘Steve Jobs in Exile’David Pogue – ’Apple: The First 50 Years’MacBook NeoLogitech MX Master 4AirPods Pro 3AirTag (2nd Generation) – 4 PackApple Watch Series 11Wireless CarPlay adapter
*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)