RUNTIME / MEDIUM

LocalAI

One OpenAI-compatible endpoint for text, vision, speech and image models, GPU optional

一手来源

DifficultyMediumSetup profile

Platforms5cpu · apple · nvidia · amd · intel

APIOpenAI + Anthropic + ElevenLabs-compatible:8080

01 / INSTALL & RUN

安装方式取决于操作系统。以下命令是示例或模板，请先替换占位符并核对量化版本、文件格式、驱动和运行时支持；内存适配不保证部署成功。

1
Installdocker run -ti --name local-ai -p 8080:8080 localai/localai:latest
2
Start a modellocal-ai run <verified-gallery-or-Hugging-Face-model-name>
3
Connect your app
OpenAI + Anthropic + ElevenLabs-compatible · :8080. Keep the service bound to localhost unless you add authentication and network controls.

注意

Backends are separate images pulled on demand, so the first run needs network access and disk. Pick the image tag for your accelerator; the CPU image does not silently enable a GPU.

02 / COMPATIBLE MODELS