
lemonade
Lemonade helps users run local LLMs with the highest performance by configuring state-of-the-art inference engines for their NPUs and GPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
Stars: 1187

Lemonade is a tool that helps users run local Large Language Models (LLMs) with high performance by configuring state-of-the-art inference engines for their Neural Processing Units (NPUs) and Graphics Processing Units (GPUs). It is used by startups, research teams, and large companies to run LLMs efficiently. Lemonade provides a high-level Python API for direct integration of LLMs into Python applications and a CLI for mixing and matching LLMs with various features like prompting templates, accuracy testing, performance benchmarking, and memory profiling. The tool supports both GGUF and ONNX models and allows importing custom models from Hugging Face using the Model Manager. Lemonade is designed to be easy to use and switch between different configurations at runtime, making it a versatile tool for running LLMs locally.
README:
Lemonade helps users run local LLMs with the highest performance by configuring state-of-the-art inference engines for their NPUs and GPUs.
Startups such as Styrk AI, research teams like Hazy Research at Stanford, and large companies like AMD use Lemonade to run LLMs.
Step 1: Download & Install | Step 2: Launch and Pull Models | Step 3: Start chatting! |
---|---|---|
![]() |
![]() |
![]() |
Install using a GUI (Windows only), pip, or from source. | Use the Model Manager to install models | A built-in chat interface is available! |
[!TIP] Want your app featured here? Let's do it! Shoot us a message on Discord, create an issue, or email.
To run and chat with Gemma 3:
lemonade-server run Gemma-3-4b-it-GGUF
To install models ahead of time, use the pull
command:
lemonade-server pull Gemma-3-4b-it-GGUF
To check all models available, use the list
command:
lemonade-server list
Note: If you installed from source, use the
lemonade-server-dev
command instead.
Tip: You can use
--llamacpp vulkan/rocm
to select a backend when running GGUF models.
Lemonade supports both GGUF and ONNX models as detailed in the Supported Configuration section. A list of all built-in models is available here.
You can also import custom GGUF and ONNX models from Hugging Face by using our Model Manager (requires server to be running).
Lemonade supports the following configurations, while also making it easy to switch between them at runtime. Find more information about it here.
Hardware | Engine: OGA | Engine: llamacpp | Engine: HF | Windows | Linux |
---|---|---|---|---|---|
🧠 CPU | All platforms | All platforms | All platforms | ✅ | ✅ |
🎮 GPU | — | Vulkan: All platforms ROCm: Selected AMD platforms* |
— | ✅ | ✅ |
🤖 NPU | AMD Ryzen™ AI 300 series | — | — | ✅ | — |
* See supported AMD ROCm platforms
Architecture | Platform Support | GPU Models |
---|---|---|
gfx1151 (STX Halo) | Windows, Ubuntu | Ryzen AI MAX+ Pro 395 |
gfx120X (RDNA4) | Windows, Ubuntu | Radeon AI PRO R9700, RX 9070 XT/GRE/9070, RX 9060 XT |
gfx110X (RDNA3) | Windows, Ubuntu | Radeon PRO W7900/W7800/W7700/V710, RX 7900 XTX/XT/GRE, RX 7800 XT, RX 7700 XT |
You can use any OpenAI-compatible client library by configuring it to use http://localhost:8000/api/v1
as the base URL. A table containing official and popular OpenAI clients on different languages is shown below.
Feel free to pick and choose your preferred language.
Python | C++ | Java | C# | Node.js | Go | Ruby | Rust | PHP |
---|---|---|---|---|---|---|---|---|
openai-python | openai-cpp | openai-java | openai-dotnet | openai-node | go-openai | ruby-openai | async-openai | openai-php |
from openai import OpenAI
# Initialize the client to use Lemonade Server
client = OpenAI(
base_url="http://localhost:8000/api/v1",
api_key="lemonade" # required but unused
)
# Create a chat completion
completion = client.chat.completions.create(
model="Llama-3.2-1B-Instruct-Hybrid", # or any other available model
messages=[
{"role": "user", "content": "What is the capital of France?"}
]
)
# Print the response
print(completion.choices[0].message.content)
For more detailed integration instructions, see the Integration Guide.
The Lemonade SDK also include the following components:
- 🐍 Lemonade API: High-level Python API to directly integrate Lemonade LLMs into Python applications.
- 🖥️ Lemonade CLI: The
lemonade
CLI lets you mix-and-match LLMs (ONNX, GGUF, SafeTensors) with prompting templates, accuracy testing, performance benchmarking, and memory profiling to characterize your models on your hardware.
To read our frequently asked questions, see our FAQ Guide
We are actively seeking collaborators from across the industry. If you would like to contribute to this project, please check out our contribution guide.
New contributors can find beginner-friendly issues tagged with "Good First Issue" to get started.
This project is sponsored by AMD. It is maintained by @danielholanda @jeremyfowers @ramkrishna @vgodsoe in equal measure. You can reach us by filing an issue, emailing [email protected], or joining our Discord.
This project is:
- Built with Python with ❤️ for the open source community,
- Standing on the shoulders of great tools from:
- ggml/llama.cpp
- OnnxRuntime GenAI
- Hugging Face Hub
- OpenAI API
- and more...
- Accelerated by mentorship from the OCV Catalyst program.
- Licensed under the Apache 2.0 License.
- Portions of the project are licensed as described in NOTICE.md.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for lemonade
Similar Open Source Tools

lemonade
Lemonade is a tool that helps users run local Large Language Models (LLMs) with high performance by configuring state-of-the-art inference engines for their Neural Processing Units (NPUs) and Graphics Processing Units (GPUs). It is used by startups, research teams, and large companies to run LLMs efficiently. Lemonade provides a high-level Python API for direct integration of LLMs into Python applications and a CLI for mixing and matching LLMs with various features like prompting templates, accuracy testing, performance benchmarking, and memory profiling. The tool supports both GGUF and ONNX models and allows importing custom models from Hugging Face using the Model Manager. Lemonade is designed to be easy to use and switch between different configurations at runtime, making it a versatile tool for running LLMs locally.

stm32ai-modelzoo
The STM32 AI model zoo is a collection of reference machine learning models optimized to run on STM32 microcontrollers. It provides a large collection of application-oriented models ready for re-training, scripts for easy retraining from user datasets, pre-trained models on reference datasets, and application code examples generated from user AI models. The project offers training scripts for transfer learning or training custom models from scratch. It includes performances on reference STM32 MCU and MPU for float and quantized models. The project is organized by application, providing step-by-step guides for training and deploying models.

palico-ai
Palico AI is a tech stack designed for rapid iteration of LLM applications. It allows users to preview changes instantly, improve performance through experiments, debug issues with logs and tracing, deploy applications behind a REST API, and manage applications with a UI control panel. Users have complete flexibility in building their applications with Palico, integrating with various tools and libraries. The tool enables users to swap models, prompts, and logic easily using AppConfig. It also facilitates performance improvement through experiments and provides options for deploying applications to cloud providers or using managed hosting. Contributions to the project are welcomed, with easy ways to get involved by picking issues labeled as 'good first issue'.

ASTRA.ai
ASTRA is an open-source platform designed for developing applications utilizing large language models. It merges the ideas of Backend-as-a-Service and LLM operations, allowing developers to swiftly create production-ready generative AI applications. Additionally, it empowers non-technical users to engage in defining and managing data operations for AI applications. With ASTRA, you can easily create real-time, multi-modal AI applications with low latency, even without any coding knowledge.

computer
Cua is a tool for creating and running high-performance macOS and Linux VMs on Apple Silicon, with built-in support for AI agents. It provides libraries like Lume for running VMs with near-native performance, Computer for interacting with sandboxes, and Agent for running agentic workflows. Users can refer to the documentation for onboarding and explore demos showcasing the tool's capabilities. Additionally, accessory libraries like Core, PyLume, Computer Server, and SOM offer additional functionality. Contributions to Cua are welcome, and the tool is open-sourced under the MIT License.

comfyui-photoshop
ComfyUI for Photoshop is a plugin that integrates with an AI-powered image generation system to enhance the Photoshop experience with features like unlimited generative fill, customizable back-end, AI-powered artistry, and one-click transformation. The plugin requires a minimum of 6GB graphics memory and 12GB RAM. Users can install the plugin and set up the ComfyUI workflow using provided links and files. Additionally, specific files like Check points, Loras, and Detailer Lora are required for different functionalities. Support and contributions are encouraged through GitHub.

TEN-Agent
TEN Agent is an open-source multimodal agent powered by the world’s first real-time multimodal framework, TEN Framework. It offers high-performance real-time multimodal interactions, multi-language and multi-platform support, edge-cloud integration, flexibility beyond model limitations, and real-time agent state management. Users can easily build complex AI applications through drag-and-drop programming, integrating audio-visual tools, databases, RAG, and more.

Olares
Olares is an open-source sovereign cloud OS designed for local AI, enabling users to build their own AI assistants, sync data across devices, self-host their workspace, stream media, and more within a sovereign cloud environment. Users can effortlessly run leading AI models, deploy open-source AI apps, access AI apps and models anywhere, and benefit from integrated AI for personalized interactions. Olares offers features like edge AI, personal data repository, self-hosted workspace, private media server, smart home hub, and user-owned decentralized social media. The platform provides enterprise-grade security, secure application ecosystem, unified file system and database, single sign-on, AI capabilities, built-in applications, seamless access, and development tools. Olares is compatible with Linux, Raspberry Pi, Mac, and Windows, and offers a wide range of system-level applications, third-party components and services, and additional libraries and components.

MaxKB
MaxKB is a knowledge base Q&A system based on the LLM large language model. MaxKB = Max Knowledge Base, which aims to become the most powerful brain of the enterprise.

LitServe
LitServe is a high-throughput serving engine designed for deploying AI models at scale. It generates an API endpoint for models, handles batching, streaming, and autoscaling across CPU/GPUs. LitServe is built for enterprise scale with a focus on minimal, hackable code-base without bloat. It supports various model types like LLMs, vision, time-series, and works with frameworks like PyTorch, JAX, Tensorflow, and more. The tool allows users to focus on model performance rather than serving boilerplate, providing full control and flexibility.

txtai
Txtai is an all-in-one embeddings database for semantic search, LLM orchestration, and language model workflows. It combines vector indexes, graph networks, and relational databases to enable vector search with SQL, topic modeling, retrieval augmented generation, and more. Txtai can stand alone or serve as a knowledge source for large language models (LLMs). Key features include vector search with SQL, object storage, topic modeling, graph analysis, multimodal indexing, embedding creation for various data types, pipelines powered by language models, workflows to connect pipelines, and support for Python, JavaScript, Java, Rust, and Go. Txtai is open-source under the Apache 2.0 license.

FalkorDB
FalkorDB is the first queryable Property Graph database to use sparse matrices to represent the adjacency matrix in graphs and linear algebra to query the graph. Primary features: * Adopting the Property Graph Model * Nodes (vertices) and Relationships (edges) that may have attributes * Nodes can have multiple labels * Relationships have a relationship type * Graphs represented as sparse adjacency matrices * OpenCypher with proprietary extensions as a query language * Queries are translated into linear algebra expressions

ASTRA.ai
Astra.ai is a multimodal agent powered by TEN, showcasing its capabilities in speech, vision, and reasoning through RAG from local documentation. It provides a platform for developing AI agents with features like RTC transportation, extension store, workflow builder, and local deployment. Users can build and test agents locally using Docker and Node.js, with prerequisites including Agora App ID, Azure's speech-to-text and text-to-speech API keys, and OpenAI API key. The platform offers advanced customization options through config files and API keys setup, enabling users to create and deploy their AI agents for various tasks.

rwkv-qualcomm
This repository provides support for inference RWKV models on Qualcomm HTP (Hexagon Tensor Processor) using QNN SDK. It supports RWKV v5, v6, and experimentally v7 models, inference using Qualcomm CPU, GPU, or HTP as the backend, whole-model float16 inference, activation INT16 and weights INT8 quantized inference, and activation INT16 and weights INT4/INT8 mixed quantized inference. Users can convert model weights to QNN model library files, generate HTP context cache, and run inference on Qualcomm Snapdragon SM8650 with HTP v75. The project requires QNN SDK, AIMET toolkit, and specific hardware for verification.

pr-agent
PR-Agent is a tool that helps to efficiently review and handle pull requests by providing AI feedbacks and suggestions. It supports various commands such as generating PR descriptions, providing code suggestions, answering questions about the PR, and updating the CHANGELOG.md file. PR-Agent can be used via CLI, GitHub Action, GitHub App, Docker, and supports multiple git providers and models. It emphasizes real-life practical usage, with each tool having a single GPT-4 call for quick and affordable responses. The PR Compression strategy enables effective handling of both short and long PRs, while the JSON prompting strategy allows for modular and customizable tools. PR-Agent Pro, the hosted version by CodiumAI, provides additional benefits such as full management, improved privacy, priority support, and extra features.

Open-Sora-Plan
Open-Sora-Plan is a project that aims to create a simple and scalable repo to reproduce Sora (OpenAI, but we prefer to call it "ClosedAI"). The project is still in its early stages, but the team is working hard to improve it and make it more accessible to the open-source community. The project is currently focused on training an unconditional model on a landscape dataset, but the team plans to expand the scope of the project in the future to include text2video experiments, training on video2text datasets, and controlling the model with more conditions.
For similar tasks

byteir
The ByteIR Project is a ByteDance model compilation solution. ByteIR includes compiler, runtime, and frontends, and provides an end-to-end model compilation solution. Although all ByteIR components (compiler/runtime/frontends) are together to provide an end-to-end solution, and all under the same umbrella of this repository, each component technically can perform independently. The name, ByteIR, comes from a legacy purpose internally. The ByteIR project is NOT an IR spec definition project. Instead, in most scenarios, ByteIR directly uses several upstream MLIR dialects and Google Mhlo. Most of ByteIR compiler passes are compatible with the selected upstream MLIR dialects and Google Mhlo.

ScandEval
ScandEval is a framework for evaluating pretrained language models on mono- or multilingual language tasks. It provides a unified interface for benchmarking models on a variety of tasks, including sentiment analysis, question answering, and machine translation. ScandEval is designed to be easy to use and extensible, making it a valuable tool for researchers and practitioners alike.

opencompass
OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features include: * Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 70+ datasets with about 400,000 questions, comprehensively evaluating the capabilities of the models in five dimensions. * Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours. * Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue-type prompt templates, to easily stimulate the maximum performance of various models. * Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded! * Experiment management and reporting mechanism: Use config files to fully record each experiment, and support real-time reporting of results.

openvino.genai
The GenAI repository contains pipelines that implement image and text generation tasks. The implementation uses OpenVINO capabilities to optimize the pipelines. Each sample covers a family of models and suggests certain modifications to adapt the code to specific needs. It includes the following pipelines: 1. Benchmarking script for large language models 2. Text generation C++ samples that support most popular models like LLaMA 2 3. Stable Diffuison (with LoRA) C++ image generation pipeline 4. Latent Consistency Model (with LoRA) C++ image generation pipeline

GPT4Point
GPT4Point is a unified framework for point-language understanding and generation. It aligns 3D point clouds with language, providing a comprehensive solution for tasks such as 3D captioning and controlled 3D generation. The project includes an automated point-language dataset annotation engine, a novel object-level point cloud benchmark, and a 3D multi-modality model. Users can train and evaluate models using the provided code and datasets, with a focus on improving models' understanding capabilities and facilitating the generation of 3D objects.

octopus-v4
The Octopus-v4 project aims to build the world's largest graph of language models, integrating specialized models and training Octopus models to connect nodes efficiently. The project focuses on identifying, training, and connecting specialized models. The repository includes scripts for running the Octopus v4 model, methods for managing the graph, training code for specialized models, and inference code. Environment setup instructions are provided for Linux with NVIDIA GPU. The Octopus v4 model helps users find suitable models for tasks and reformats queries for effective processing. The project leverages Language Large Models for various domains and provides benchmark results. Users are encouraged to train and add specialized models following recommended procedures.

Awesome-LLM-RAG
This repository, Awesome-LLM-RAG, aims to record advanced papers on Retrieval Augmented Generation (RAG) in Large Language Models (LLMs). It serves as a resource hub for researchers interested in promoting their work related to LLM RAG by updating paper information through pull requests. The repository covers various topics such as workshops, tutorials, papers, surveys, benchmarks, retrieval-enhanced LLMs, RAG instruction tuning, RAG in-context learning, RAG embeddings, RAG simulators, RAG search, RAG long-text and memory, RAG evaluation, RAG optimization, and RAG applications.

stm32ai-modelzoo
The STM32 AI model zoo is a collection of reference machine learning models optimized to run on STM32 microcontrollers. It provides a large collection of application-oriented models ready for re-training, scripts for easy retraining from user datasets, pre-trained models on reference datasets, and application code examples generated from user AI models. The project offers training scripts for transfer learning or training custom models from scratch. It includes performances on reference STM32 MCU and MPU for float and quantized models. The project is organized by application, providing step-by-step guides for training and deploying models.
For similar jobs

sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.