Skip to content
← Tools / Skills
ToolElement Labs/10 trustVerified
LM Studio logo

LM Studio

Desktop app to download, run, and chat with LLMs locally via an OpenAI-compatible API.

Visit official site →

About

LM Studio is a desktop application for macOS, Windows, and Linux that runs large language models locally. It offers a polished GUI with a Hugging Face model browser, automatic hardware detection, GPU offloading, and a local server exposing OpenAI-compatible endpoints so any app can call the local model.

Since version 0.3.17 (June 2025), LM Studio acts as an MCP host, letting users wire MCP servers into local-model chats. In April 2026 Element Labs acquired Locally AI, extending the story to iPhone and iPad via the Locally mobile app and LM Link, an encrypted bridge that lets a phone drive models running on a desktop. Limitation: it is a single-user local tool with no built-in authentication or rate limiting, so it is not a production serving solution.

What it can do

  • One-click Hugging Face model downloads (GGUF, MLX)
  • OpenAI-compatible local API server
  • MCP host for tool-using local agents
  • Hardware-aware GPU offloading and memory management

Setup

Download the installer from lmstudio.ai for your OS and install; press Cmd/Ctrl+Shift+R to install runtimes.

Prerequisites

A desktop or laptop with 16GB+ RAM recommended; Apple Silicon or x64 with AVX2.

Use cases

local-llmllm-inferenceprototyping

Works with

Trust score — 8/10

/10 trustVerified

Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 63; Trending score 85/100 from researcher assessment.

Sources

Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.