DOA
Help me choose

Local AI › Tools to run AI locally: Ollama, LM Studio, Jan and more

Tools to run AI locally: Ollama, LM Studio, Jan and more

Seven free tools to run AI on your own computer, from the easiest (LM Studio, Ollama) to the most technical (llama.cpp, ComfyUI).

Checked on 13 Oct 2026. Versions change every week: check the official site before installing.

ToolOperating systemsLicence and priceEase of useCurrent version
OllamaWindows, macOS and LinuxMIT · freeVery easyv0.40.3 (11 Oct 2026)
LM StudioWindows (x64 with AVX2 or Arm64), macOS 14+ on Apple Silicon and Linux (AppImage and .deb)Free · proprietary software (terms of use)Very easy0.4.26
JanWindows, macOS and Linux (.deb, AppImage and Arm64)Apache 2.0 · freeEasyv0.8.6 (9 Oct 2026)
GPT4AllWindows, macOS and LinuxMIT · freeEasyv3.10.0 (25 Feb 2025) · low activity
llama.cppWindows, macOS and LinuxMIT · freeTechnicalv0.6.0 (5 Oct 2026)
Open WebUIAny system with Docker or PythonOpen WebUI License (BSD-3 style with a branding clause) · freeMediumv0.12.0 (10 Oct 2026)
ComfyUIWindows, macOS and Linux (desktop app, portable build or manual install, per the README)GPL-3.0 · freeTechnicalv0.39.0 (5 Oct 2026)

Versions: latest release on GitHub (LM Studio: its download page). Licences: each repository's LICENSE file or the official terms. Ease of use is DOA's editorial rating.

What each one is

  • Ollama: Engine and app to download and run language models with a single command. It includes a local API so other apps can connect to it.
  • LM Studio: Desktop app with a graphical interface to find, download and chat with models in GGUF or MLX format. It also has a local server.
  • Jan: Open-source desktop app to chat with models offline, ChatGPT-style.
  • GPT4All: Nomic's desktop app to chat locally and ask questions about your own documents (LocalDocs). Low activity.
  • llama.cpp: C/C++ library and command-line tools that many apps are built on and that define the GGUF format. The most technical option.
  • Open WebUI: Self-hosted, ChatGPT-style web interface that connects to Ollama or OpenAI-compatible APIs.
  • ComfyUI: Node-based interface to generate images and video with open models on your own computer.

Keep reading