AI WikiAI Wiki
LM Studio logo

LM Studio

Free tier

Run AI models locally and privately on your own hardware

Free tier available·All audiences·Powered by Multiple (Qwen, Gemma, DeepSeek, GPT-OSS, Apple MLX, etc.)·API available
Visit

Key strengths

Fully local & private — no data leaves your machineSupports a wide range of open-source LLMs (Qwen, Gemma, DeepSeek, MLX, etc.)OpenAI-compatible API for seamless developer integrationHeadless/server deployment via llmstер CLI toolOfficial JavaScript and Python SDKs with MCP client support
Free tier + paid plans
United States
Self-hostable
No ratings yet
  • Local LLM API server — Spin up an OpenAI-compatible endpoint on localhost and integrate local models into existing apps without changing client code.
  • CI/CD pipeline inference — Use the headless llmster binary in automated pipelines (e.g., GitHub Actions) to run model inference without a desktop environment.
  • SDK-powered agent workflows — Build LLM-powered agents and multi-step pipelines using the official lmstudio-js or lmstudio-python SDKs with full async support.
  • Apple Silicon acceleration — Load Apple MLX models for highly optimized, GPU-accelerated inference on M-series Macs.
  • MCP tool integration — Use LM Studio as an MCP client to give local models access to external tools, databases, and services in agentic workflows.
  • Air-gapped / compliance environments — Deploy LLMs in fully offline or network-restricted environments where sending data to external APIs is prohibited.