👾 LM Studio - Discover and run local LLMs

🚀 Dive into the world of local LLMs with LM Studio! 🌟 Experiment with powerful models from Hugging Face offline, with GPU support for enhanced performance. 🤖💻 Perfect for enthusiasts and professionals alike! #AI #LMStudio #HuggingFace #LLMs

LM Studio is a tool for running local LLMs like LLaMa Falcon, MPT Gemma, Replit GPT-Neo-X, and gguf ⓘ models from Hugging Face.
It supports Google DeepMind's Gemma (2B, 7B) starting from version 0.2.16 for Mac (M1/M2/M3), Windows, and Linux.
New in version 0.2.16 is the Google Gemma support, along with an improved downloader.
Users can run LLMs offline, use in-app Chat UI, and download models from Hugging Face repositories.
LM Studio supports various models like Llama, MPT, and StarCoder on Hugging Face.
Minimum requirements include M1/M2/M3 Mac, Windows PC with AVX2 support, and Linux in beta.
Privacy is a priority, as LM Studio does not collect data and keeps all information local on the user's machine.
For business use, there is a separate request form available.
The team behind LM Studio is hiring, with open positions listed on their website.
Hardware/software requirements vary based on the system, with specific guidelines for Apple Silicon, Windows, and Linux PCs.
The tool is free for personal use, and new features are continuously being developed.
LM Studio is based in Brooklyn, New York, and welcomes inquiries about using the tool in a professional setting.