LM Studio

Desktop app for macOS, Windows and Linux that finds, downloads and runs open models locally (GGUF through llama.cpp, MLX on Apple Silicon), with chat, offline document chat, MCP tools and an OpenAI-compatible local server.

Visit Website
Pricing Free
Category Infrastructure
Local LLM Desktop App MLX GGUF API

Founder's Verdict

"The friendliest way to run local models if you'd rather click than type. Search Hugging Face, chat, then turn on a local server for your apps. Free for home and work, though the app itself isn't open source."

LM Studio

LM Studio is a desktop app for running open models on your own machine. It supports Apple Silicon Macs, x64 and ARM64 Windows PCs, and x64 Linux PCs.

What it does

  • Finds and downloads models for you, with Hugging Face search built into the app.
  • Two engines. GGUF models run through llama.cpp on every platform, and MLX models run on Apple Silicon Macs.
  • Chat, including with your documents, entirely offline.
  • Serves models to your apps through OpenAI-compatible endpoints, on your machine or across your network, plus a beta LM Studio REST API.
  • Uses tools through MCP. Install MCP servers and use them with local models.
  • Developer tooling: the lms command-line tool, Python and TypeScript SDKs, and llmster, a headless build for servers and CI.

LM Studio’s newest product is Bionic, an agent for open models that works on documents, code and automations, built on the same runtime.

Price and license

  • Free at home and at work. Since 8 July 2025, LM Studio’s terms no longer require a separate license or form for company use (announcement).
  • Teams and Enterprise plans add private sharing, SSO, and model and MCP gating. Prices aren’t published.
  • Not open source. The desktop app is closed source. Its lms CLI, SDKs and MLX engine are MIT-licensed on GitHub.

Who it’s for

  • People who want local AI without the terminal.
  • Mac users who want MLX models alongside GGUF.
  • Developers who want a local OpenAI-compatible endpoint and a GUI for managing models.

Alternatives

Want something scriptable and fully open source? Try Ollama, or llama.cpp, the engine LM Studio uses for GGUF models. See all three side by side in Ollama vs LM Studio vs llama.cpp.

Compared with

Ollama vs LM Studio vs llama.cpp (2026): Best Way to Run LLMs Locally Start with Ollama if you want local models behind an API for your apps and coding agents: it's MIT-licensed and a one-line install on macOS, Windows and Linux. Pick LM Studio if you'd rather work in a desktop app, especially on an Apple Silicon Mac, where it also runs MLX models. Use llama.cpp directly when you want the engine itself, with the most control over hardware backends and quantization.

Related Tools

DeepSeek

Chinese AI lab whose chat app runs on DeepSeek-V4.1-Flash, with web, mobile and desktop apps. Its models are open weights under the MIT license, and its API is among the cheapest frontier-class options.

ChatAI Assistant

llama.cpp

★133k

The open-source C/C++ engine for running LLMs and vision models locally, with a CLI, an OpenAI-compatible server with a built-in web UI, 1.5-bit to 8-bit quantization, and backends from CUDA and Metal to Vulkan and SYCL.

Local LLMOpen Source

Ollama

★185.5k

Run open models such as Gemma, Qwen, DeepSeek and gpt-oss on your own computer with one command, then use them through a local REST API, Python or JavaScript, or coding agents like Claude Code and Codex. Optional cloud models cover anything too big for your hardware.

Local LLMOpen Source