LM Studio — awesome-ai-stack

Overview

LM Studio is a desktop application (macOS, Windows, Linux) for discovering, downloading, and running local LLMs in GGUF and MLX formats, with a chat UI and a built-in server.
The server is OpenAI-compatible, so your existing code — or LiteLLM — can point at localhost instead of a cloud provider. It is free for personal and commercial use.

flowchart LR
  hub[model catalog] --> lms[LM Studio]
  lms --> chat[chat UI]
  lms --> server[(OpenAI-compatible server)]
  server --> app[your app]

The Code samples tab shows calling the local server.

When to use it

Choose LM Studio when you want the easiest way to run models locally with a GUI — browsing, downloading, and serving — rather than a CLI runtime like Ollama or a GPU serving engine like vLLM.

Pricing

Free for personal and commercial use. Optional paid Teams/Enterprise for SSO, gating, and private collaboration

Source ↗ · as of 2026-06-27

Example

Shell · local server

When to use

Use LM Studio when you want a friendly desktop UI to browse and run local models, plus a drop-in OpenAI-compatible endpoint for your code.

# In the LM Studio app: download a model, then start the local server.
# It exposes an OpenAI-compatible API at http://localhost:1234/v1
curl http://localhost:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "local-model",
       "messages": [{"role": "user", "content": "Say hello."}]}'

Related tools

Overview

When to use it

Pricing

When to use