Native development cambrian explosion hasn’t really started yet
Super fast Qwen3.8 27B on Mac
Qwen3.8-27B, up to 144 tok/sec on M5 Max.
Let that sink in. ⚡️✨🚀
Excited to partner with @inco_ai to bring you their Splash inference engine in LM Studio on day 0!
Get it running now:
Show more
Qwen3.8-27B, up to 144 tok/sec on M5 Max.
Let that sink in. ⚡️✨🚀
Excited to partner with @inco_ai to bring you their Splash inference engine in LM Studio on day 0!
Get it running now:
Show more
Qwen3.8-27B at 144 tok/s on an M5 Max MacBook Pro ⚡
Meet Inco Splash: our open-source inference engine, built around the model and around Apple silicon.
Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents.
Show more
Introducing Introspection and Session References
Bionic agent can now search through its own session history, making it much more capable of handling long-term context and multiple compactions.
You can also reference other sessions directly in the composer using an @ mention!
Show more
Introducing local realtime voice transcription.
Speak freely to your agents, without sending your voice data to the cloud.
Available for Mac, Windows - and now also Linux!
With iOS 27 Apple introduced its most powerful on-device model: AFM 3 Core Advanced
It’s a 20 billion parameters model activating only between 1 to 4 billion parameters depending on the request
Here’s the model running on iPhone 17 Pro
Show more
Locally is ready for iOS 27!
Revisit the app with refined Liquid Glass and try Apple’s new on-device foundation models, now with vision support.
Available now.
Now live in LM Studio Bionic!
Bionic 1.1.2 just shipped!
You should feel noticeable performance improvements across the board, and especially for session loading and tab switching. Also contains a number of fixes for screen reader users, with more on the way.
Show more
I wrote about the state of AI, why I’m concerned about the next few years, and the choices we need to make to keep the future in humanity’s hands.
An Alien Mind:
I replaced Claude with LM Studio Bionic — and I’m not going back
The announcement of @nvidia's acquisition of @huggingface on the same morning that Claude, ChatGPT, and Grok are all down shows the importance of owning your AI. Glad we'll have such a strong open model ecosystem with nvidia and HF joining forces.
Show more
Bionic is up. Continue your work.
The age of local agents is here and it’s just getting started
