Lemonade Server
Local AI server for LLMs, speech and images, tuned for AMD Ryzen AI NPUs and Radeon GPUs
Lemonade Server is a local AI server for text, speech and image models, with optimizations from AMD engineers for Ryzen AI NPUs and Radeon GPUs. It serves OpenAI-, Anthropic- and Ollama-compatible APIs on localhost.
Backends include llama.cpp (Vulkan, ROCm, CUDA, Metal, CPU), NPU engines for Ryzen AI XDNA2 chips, whisper.cpp and stable-diffusion.cpp. It loads GGUF, FLM and ONNX models.
It runs on Windows, Linux, macOS and Docker. Apache-2.0, community-maintained and sponsored by AMD.
Pricing: Free
Choosing a local LLM runtime right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a local LLM runtime right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Lemonade Server Alternatives
Explore 49 products in the Frameworks & Stacks category. View all Lemonade Server alternatives.
GPT4All
Desktop app and Python SDK for running open-source LLMs locally on any device
LocalAI
Open-source, self-hosted OpenAI-compatible API for running models on your own hardware
Jan
Open-source desktop app for running LLMs locally with a clean GUI
TextGen
Formerly text-generation-webui: open-source desktop app and web UI for local LLMs with an OpenAI-compatible API
Dify
Easily build and operate generative AI applications. Create Assistants API and GPTs based on any LLMs.
Work on Lemonade Server? Feature it at the top of Frameworks & Stacks.
Is your product missing?