// INFERENCE RUNTIME

LM Studio

Desktop GUI for discovering, downloading, and running local LLMs. Includes an OpenAI-compatible local server and chat interface. Powered by llama.cpp and MLX backends.
Platforms
Windows, macOS, Linux
Backends
CUDA, Metal, Vulkan, CPU
Quant formats
GGUF (all variants), MLX
LM Studio website ↗

Videos about LM Studio

LM Studio Tutorial: Run Large Language Models (LLM) on Your Laptop

Run ANY Open-Source Model LOCALLY (LM Studio Tutorial)

LM Studio Tutorial & Review – The Best Way to Run AI Locally

FAQ

What platforms does LM Studio support?▶

LM Studio runs on Windows, macOS, Linux with backends CUDA, Metal, Vulkan, CPU.

What quant formats does LM Studio support?▶

LM Studio supports GGUF (all variants), MLX.

→ All runtimes→ Hardware