RUNTIME / EASY

Lemonade

Ryzen AI, Radeon and Strix Halo PCs, including the XDNA2 NPU, behind one local API

一手来源

DifficultyEasySetup profile

Platforms4amd · nvidia · cpu · apple

APIOpenAI + Ollama + Anthropic-compatible:13305

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
Installsnap install lemonade-server # or the .msi / .deb / .pkg installer
2
Start a modellemonade run <verified-model-name>
3
Connect your app
OpenAI + Ollama + Anthropic-compatible · :13305. Keep the service bound to localhost unless you add authentication and network controls.

注意

Built with AMD engineers around Ryzen AI, Radeon and Strix Halo; CUDA, Vulkan, Metal and CPU backends cover other PCs. Run `lemonade backends` on the machine itself — the NPU path needs the vendor driver stack and is not available everywhere.

02 / COMPATIBLE MODELS