Run This Ai
EN DE

Lemonade

Run optimized LLMs locally on your own GPU or NPU — a fast, OpenAI-compatible server for private AI apps.

★ 5,385 GitHub Apache-2.0 local-aillmgpunpuonnxopenai-apiprivacy LLM & Chat

Overview

Lemonade helps you discover and run local AI apps by serving optimized LLMs directly from your own GPU or NPU. It is a lightweight, OpenAI-compatible local server that keeps your data private while delivering fast inference on consumer hardware. Built on ONNX Runtime with Vulkan, ROCm, and NPU acceleration, it supports models like Llama, Mistral, and Qwen without cloud dependencies.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  lemonade:
    image: ghcr.io/lemonade-sdk/lemonade:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/lemonade:/data

Best VPS for Lemonade →

Related tools

NextChat

Cross-platform ChatGPT web UI with multi-model support for Ollama, Claude, Gemini, and more

Lobe Chat

Extensible, open-source ChatGPT alternative with plugins, knowledge base, and multi-LLM support

Open WebUI

User-friendly WebUI for LLMs (Ollama, OpenAI API)

text-generation-webui

Run local LLMs with a powerful web interface — text, vision, tool-calling, and OpenAI-compatible API

Streamlit

Build and share data apps in pure Python — fast

Gradio

Build and share delightful machine learning apps in Python

Guides & articles

Getting Started with Lemonade: Local LLMs in Minutes

Step-by-step tutorial: deploy Lemonade with Docker, download an optimized local LLM, and connect your apps via the OpenAI-compatible API — fully offline.

Aug 17, 2026

Lemonade: Run Local AI Apps on Your Own GPU

Lemonade is an open-source local AI server that runs optimized LLMs on your own GPU or NPU. Discover how it delivers private, OpenAI-compatible inference with 5.4K+ GitHub stars.

Aug 17, 2026