RUNTIME / EASY

Lemonade

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

Primärquelle

DifficultyEasySetup profile

Platforms4amd · nvidia · cpu · apple

APIOpenAI + Ollama + Anthropic-compatible:13305

01 / INSTALL & RUN

Installation depends on your OS. These commands are examples or templates: replace placeholders and verify quantization, file format, drivers and runtime support. Memory fit does not guarantee deployment.

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.

Achtung

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