
Run local models on AMD GPUs and NPUs, with OpenAI-style APIs
Do you work on Lemonade Server?
This listing is unclaimed. Claim it for free to edit the details, add screenshots and reply to reviews.
Lemonade Server is AMD's open-source local AI serving platform for LLMs, image generation, speech recognition and text-to-speech on your own hardware. It is aimed at people who want local AI on Ryzen AI, Radeon or Strix Halo PCs. It detects CPU, GPU and NPU backends, is written in lightweight C++, and exposes OpenAI, Anthropic and Ollama-compatible APIs. A desktop model manager is included. It supports GGUF, FLM and ONNX models on Windows, Linux, macOS and Docker, and it is listed as free.
From people who have used it. One review per person, checked by a human.
No reviews yet. Be the first to say something useful.