LM Studio

Thrilled to be featured in Apple's new 512GB Mac Studio product page! ??????

LM Studio is a fantastic tool for discovering, downloading, and running local LLMs right on your machine. It works with Mac, Windows, or Linux... and it is FREE. With it, you can: ?? Run LLMs on your laptop, entirely offline ?? Chat with your local documents (new in 0.3) ?? Use models through the in-app Chat UI or an OpenAI compatible local server ?? Download any compatible model files from Hugging Face ?? repositories ?? Discover new & noteworthy LLMs right inside the app's Discover page Give it a shot here: https://lmstudio.ai/

Google's Gemma 3 models are now available to download and run in LM Studio! ?????? 4B, 12B, 27B Gemma 3 models support both text and image inputs. Built from the same research & tech Google DeepMind used for the Gemini models!

So, I stumbled across something pretty cool today. LM Studio just dropped Python and TypeScript SDKs for local LLMs. What caught my eye is their new agent-oriented API with this .act() call. Basically, you hand it a task and some tools, and then the model autonomously does its thing until it completes what you asked it to do. It's like hiring a tiny digital contractor who works in "rounds" until the job is done. Both libraries are MIT-licensed and open source on GitHub, which is always a plus in my book. You'll need LM Studio version 0.3.11 to make it work. Getting it set up is pretty straightforward. Python: pip install lmstudio JS/TS: npm install @lmstudio/sdk I've been messing around with local LLMs lately because, well, what engineer wouldn't? The cloud is someone else's computer, but my computer is right here, and I like having my models where I can see them. This SDK seems like it could cut through a lot of the implementation headaches. Is anyone else planning to build something with this? I'm curious what people might come up with! Do you wanna build a (snowman…) I mean, agent tool, automation system, or perhaps something I haven't even thought of yet?

No way! LM Studio mentioned in Apple’s new 512GB Mac Studio product page! ????

How do you predictably enforce the output format from an open source local model? ?? Use Pydantic and lmstudio-python ?? Learn more: https://lnkd.in/e6iCRZ9i

Announcing the LM Studio SDK for Python and TypeScript! As a part of the SDK, we also introduce our first agent-oriented API: the .act() call. You provide a task and tools, and the model goes on its own autonomously for multiple turns until it accomplishes the task. Read all about it in the announcement blog post: https://lnkd.in/es2hG_sz

Something big for local LLM builders is coming in the next few hours! ????

Introducing LM Studio 0.3.10 with ?? Speculative Decoding! It's an LLM inferencing technique that can speed up token generation by up to 1.5x-3x in some cases ????? - Supported for both GGUF and MLX models - Available in both LM Studio's Chat UI and API Get LM Studio 0.3.10 from https://lmstudio.ai

The team has been hard at work on a new feature for you all! Can you ...speculate... what it might be? ????