Open-source desktop app to run, serve and fine-tune text, image, video and audio models entirely on your own machine.
Free
Summary
A polished desktop app for discovering, running, and chatting with local language models — no terminal required.
Description
LM Studio is the graphical answer to running models on your own hardware. It bundles model discovery, download, chat, and a local server into one desktop application for macOS, Windows, and Linux, and it is deliberately approachable for people who do not want to think about quantisation formats or command-line flags.
What you get
- In-app model search across the open-weight catalogue, with clear guidance about which quantisations will actually fit your RAM and GPU
- A full chat interface with system prompts, conversation branching, attachments, and per-model parameter controls
- A local OpenAI-compatible server so your own scripts, editors, and agent frameworks can call the model you have loaded
- Document chat that indexes local files for retrieval without uploading them anywhere
- Hardware-aware defaults that pick reasonable GPU offload settings instead of making you guess
Who it suits
People evaluating open models before committing to one, privacy-sensitive work where cloud APIs are not an option, and developers who want a dependable local endpoint with a UI attached. Free to download and use.
Reviews
Similar App Suggestions
Spotify's vendor-neutral workspace for running dozens of Claude Code, Codex and Gemini CLI sessions in parallel with shared context.
Free
A coding agent tuned for latency: routes easy work to fast models, pulls only the code it needs, and fans out tool calls in parallel.
Free
Run agent evals and private benchmarks in sandboxed cloud environments — compare Claude Code, Codex, Cursor and Copilot on the same real tasks.
Freemium
An open-source proxy that sits between your coding agent and the model, compressing tool schemas, file reads and stale history to cut token bills.
Freemium