@meta
  v: 1
  route: /runtime/lm-studio
  generated: 2026-06-10T09:17:15.097Z

@intent
  purpose:    Install, configure, and serve LLMs with LM Studio.
  audience:   self-hoster, ai-engineer, mac-user, devops-engineer
  capability: install, serve_local_llms, compare_runtimes, open_external_docs

@state
  slug: lm-studio
  name: LM Studio
  family: cross-platform
  type: gui
  license: Proprietary (free for home and work use)
  primary_platform: macOS · Linux · Windows
  platforms[3]: macOS, Linux, Windows
  model_formats[2]: GGUF, MLX
  api_compatibility[3]: OpenAI-compatible, JS SDK, Python SDK
  install_command: curl -fsSL https://lmstudio.ai/install.sh | bash
  install_secondary: Or download the GUI app from lmstudio.ai (Mac / Win / Linux)
  homepage_url: https://lmstudio.ai
  github_url: https://github.com/lmstudio-ai
  docs_url: https://lmstudio.ai/docs
  feature_count: 4
  feature_labels[4]: GUI app, llmster headless, LM Link, SDKs
  best_for[4]: Users who want a GUI for browsing and trying models, Apple Silicon (first-class MLX support alongside GGUF), "Quick experimentation: download, load, chat in three clicks", Headless deployment via `llmster` on servers and CI
  caveats[3]: "Not open source (proprietary license, free use only)", In-memory KV cache; long agentic sessions can churn, "No native tool-calling parity with the agent-focused servers (oMLX, vLLM)"

@actions
  - id: open_homepage
    method: GET
    href: https://lmstudio.ai
  - id: open_github
    method: GET
    href: https://github.com/lmstudio-ai
  - id: open_docs
    method: GET
    href: https://lmstudio.ai/docs
  - id: view_index
    method: GET
    href: /runtime/
  - id: view_calculator
    method: GET
    href: /#calculator

@context
  > Desktop app for browsing, downloading, and chatting with local LLMs. Supports GGUF and MLX formats. Now ships `llmster`, a no-GUI deployment binary for Linux boxes, cloud servers, and CI. Free for home and work use. Strong onboarding for users new to local inference; popular on Apple Silicon thanks to MLX support.

@nav
  self:      /runtime/lm-studio
  parents:   [/, /runtime/]
  peers:     [/runtime/ollama, /runtime/vllm, /runtime/mlx, /runtime/omlx]
  drilldown: /#calculator