mudler /LocalAI

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

★ 50,390⑂ 4,610👁 299⑃ 5,908● 1,676▤ 141
GoMITCreated 2023-03-18localai.io
下载:v4.12.1v4.12.1 ↓4.12.12026-10-23
+24
日增长
+121
周增长
50,390
stars
4,610
forks
299
watchers
5,908
prs
1,676
issues
141
releases

README

Documentation |
Quick start |
Models |
Discord |
FAQ |
Blog


LocalAI is your own AI, on your own hardware, ready to work for you. It is open source. Chat with open models, run agents that use your files, and work on documents with your team. It also does voice, images, video and more. No GPU required.

- Agents, documents and a team: chats and saved agents that use tools, MCP servers, files, collections and skills. Users, roles, quotas and shared folders for a team (development builds).
- Add-ons: an admin installs add-ons from a library: Office, Sandbox, Tables, chat apps (Telegram, Slack, Discord), mail, calendar and more (development builds).
- Every kind of model, one API: text, vision, voice, images, video and embeddings, in the OpenAI, Anthropic and ElevenLabs formats, with more than 80 backends. Each backend is its own image, pulled only when a model needs it.
- Your hardware: NVIDIA, AMD, Intel, Apple Silicon, Vulkan, NVIDIA Jetson or CPU only. The server, the models and your files stay on your own machines.

!LocalAI is a small core with an API, chats and agents, files, collections, team sharing, a model gallery and an MCP client and server for agent tools. Backends such as llama.cpp, vLLM, MLX and whisper.cpp plug in on one side, add-ons such as Office, Sandbox, Tables and chat apps on the other. It runs on CPU, NVIDIA, AMD, Intel, Apple Silicon and Vulkan.

Created by Ettore Di Giacinto and maintained by the LocalAI team.

 Quick start

Script (Linux, and macOS on Apple Silicon): it downloads the release binary for your machine and checks it against the release checksums.

bash
curl -sSL https://localai.io/install.sh | sh
local-ai run qwen3-4b


Container (Docker, podman, ...):

bash
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest


Desktop app: the launcher installs and updates the server for you, on Linux (AppImage) and macOS (DMG). Download LocalAI.dmg or the AppImage from the releases page and see the desktop app guide.

The script, the app and the latest container image give version 4.12.1. The add-ons, Office, Sandbox and team features described below need a development build or a newer release.

Then open http://localhost:8080. To restart an existing container, use docker start -i local-ai. More ways to install: Install LocalAI.


GPU images (NVIDIA, AMD, Intel, Vulkan)

bash
 NVIDIA, CUDA 13
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-gpu-nvidia-cuda-13

 NVIDIA, CUDA 12
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-gpu-nvidia-cuda-12

 NVIDIA Jetson ARM64 (CUDA 12, for AGX Orin and similar)
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-nvidia-l4t-arm64

 NVIDIA Jetson ARM64 (CUDA 13, for DGX Spark)
docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-nvidia-l4t-arm64-cuda-13

 AMD (ROCm)
docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video lo

Top issues

Discussions

Latest release

v4.12.1 v4.12.1 2026-10-23
Patch release v4.12.1. Security fix only.

Security

- Hardened the external URL policy for user-supplied URLs (chat vision image/audio/video URLs, image and audio endpoints). Redirect targets are now validated on every hop, 100.64.0.0/10 and 0.0.0.0/8 are treated as non-public, and the connection goes to the address that was validated. See 12853. Credits to @spicysharkco for the discovery.

Full Changelog: https://github.com/mudler/LocalAI/compare/v4.12.0...v4.12.1

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON