Self-hosted runtime

LM Studio

LM Studio is a desktop app for downloading and running open-weight models on your own computer.

Website (opens in a new tab)

Checked 2026-10-31

LM Studio is a desktop app for downloading and running open-weight models on your own computer. Its docs say it supports Apple Silicon Macs, x64 and ARM64 Windows PCs, and x64 Linux PCs, running llama.cpp GGUF models and MLX models on Apple Silicon. It includes a chat window, MCP server support and model search through Hugging Face. It can serve local models on OpenAI-style endpoints, with chat completions documented at http://localhost:1234/v1, and the headless version, called llmster, runs without the desktop app. A July 2025 post says LM Studio is free to use at home and at work. The terms say certain features may be offered for a fee. The software is proprietary, not open source, and the terms bar reverse engineering and creating derivative works, so we list no open-source license. We would suggest it to people who want a polished app and a local endpoint. The limit is that you cannot read or modify the source of the app. We have not run it ourselves for this note.

Mentioned here

Questions

How much does LM Studio cost?

Free to use at home and at work, per LM Studio's July 2025 announcement; some add-on features may be offered for a fee under its terms (checked 31 October 2026).

Is LM Studio OpenAI compatible?

Yes, it offers an OpenAI-compatible API, so most agents and SDKs can point at it by changing the base URL.

Can I self-host LM Studio?

Yes, it can run on your own servers.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • Text Generation Inference

    Text Generation Inference, or TGI, is Hugging Face's open server for running large language models on your own GPUs.

    • Self-hosted runtime
    • OpenAI compatible
    • Self-hostable

  • vLLM

    vLLM is a high-throughput, memory-efficient serving engine for large language models, run as a server you host yourself.

    • Self-hosted runtime
    • OpenAI compatible
    • Self-hostable

  • LocalAI

    LocalAI is an open-source runtime that runs AI models on your own hardware.

    • Self-hosted runtime
    • OpenAI compatible
    • Self-hostable

  • SGLang

    SGLang is a serving framework for large language and multimodal models, aimed at low latency and high throughput from a single GPU up to large clusters.

    • Self-hosted runtime
    • OpenAI compatible
    • Self-hostable