Locally AI - Local AI Chat
@LocallyAIApp
Run AI models like Gemma, Qwen, and more locally on your iPhone, iPad and Mac. By @lmstudio.
66 Following 14.8K Followers
Gemma 4 Mobile is now available on iPhone and iPad!
This model is a variant optimized for mobile use cases and comes with a reduced memory footprint. Running natively with MLX.
And congrats to @googlegemma on reaching 1 billion downloads! 🎉
Show more
The new LFM 2.5 2.6B model by @liquidai is now available on iPhone and iPad.
A fast model designed for edge devices with comparable or better scores compared to models up to nearly 4× its size.
Update your app now.
Show more
Try 1-bit Bonsai 27B, the latest model from
@PrismML on Mac.
This model pushes the limits of intelligence density, packing 27B parameters into just 5 GB. Powered by MLX.
Available now.
Show more
Meet 1-bit Bonsai 27B, the latest model from @PrismML and the first 27B-class model to run on a phone.
This model, available on the iPhone 17 Pro, iPhone Air, and select iPads, pushes the limits of intelligence density. Powered by MLX.
Available now.
Show more
With today's update, devices that don’t support on-device models can now use the app with LM Link.
Connect remotely to any model running on your computer with @lmstudio 👾
Locally is now @lmstudio's mobile app, and we are bringing LM Link to your iPhone.
Use your largest models from your phone, over a secure, end-to-end encrypted connection.
Available on iPhone and iPad.
Show more
Today.
Pinned conversations are now available on macOS.
This update also includes bug fixes, performance enhancements, and more.
Update your app now.
Improvements to the app in iPad Windowed Apps mode, pinned conversations, bug fixes, performance enhancements, and more in the latest update.
Now available on iOS and iPadOS.
The next update will focus on improvements and bug fixes across the app.
Coming next week. Stay tuned.
The new LFM 2.5 VL 450M model by @liquidai is now available in the app.
A lightning-fast and lightweight model perfect for image understanding in shortcuts.
Update your app now.
Show more
The new Qwen 3.6 27B model by @Alibaba_Qwen is now available for compatible Macs.
The model matches Claude 4.5 Opus across various benchmarks.
This update also includes Ternary Bonsai 8B from @PrismML, along with performance improvements.
Show more
Try the new Ternary Bonsai 8B from @PrismML.
A larger, smarter Bonsai model available on iPhone and iPad.
Update your app now.
The Gemma 4 26B A4B and 31B models are now available on Mac with the latest update!
The largest and most intelligent models currently available in the app.
This update also improves and fixes issues with Gemma 4 on compatible iPhones and iPads.
Show more
Today, we’re excited to announce that we’re joining @lmstudio!
We share a common vision of building amazing products for everyone and making local models more accessible.
We’re combining our efforts to bring you the best experience possible.
Show more
Supercharge your shortcuts with LFM 2.5 350M by @liquidai.
A fast, efficient, low-latency model built for shortcuts.
Available in the app.
