#52 · Primary category： Inference & Local Deploy
lemonade
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
Project last updated：08/30/26
GitHub Stars
5.5K
Forks
479
Contributors
131
License
Apache-2.0
Why we included this project
Lemonade turns a PC's own NPU or GPU into a local AI server that speaks the same OpenAI, Anthropic, and Ollama APIs as cloud services, so existing clients and tools can point at it without rewiring integrations. It handles chat, coding, speech, and image generation on-device, with optimizations that lean hardest on AMD hardware such as Ryzen AI, Radeon, and Strix Halo. A model manager pulls GGUF, FLM, and ONNX weights from Hugging Face or ModelScope, and the server ships as Windows, Linux, macOS, and Docker installers. There is also an embeddable binary that packages multi-modal inference into your own application and auto-tunes for each user's machine, which makes it a practical fit for desktop tools and privacy-sensitive workflows that want cloud-style capabilities without sending data anywhere.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.