Build with Liquid AI models and the Liquid Edge AI Platform
🌊 Liquid Docs | 🤗 Hugging Face | 🚀 Liquid Edge AI Platform
This repository contains examples, tutorials, and applications built with Liquid AI open-weight models (LFM) and the open-source LEAP SDK.
Whether you're looking to customize models, deploy to laptops, edge devices, or build complete applications, you'll find resources here to get started.
-
Examples of local AI applications 🤖 that showcase the power of our LFM model family.
-
Fine tuning notebooks and examples 🎯 to increase the performance of LFM2 models for your specific use case.
-
Deployment to iOS and Android devices 📱 with the LEAP SDK
-
End-to-end tutorials 📚 that cover the whole path from data collection, evaluation, fine-tuning and deployment.
-
Examples built by our growing community 🌟 that showcase what is possible with Liquid AI models.
-
60-minute technical deep dives on all-things-efficient-AI every month in the Liquid Discord community.
| Name | What's that? |
|---|---|
| 🧾 invoice-parser | A Python CLI that extracts structured data from invoice pdfiles using LFM2-VL-3B |
| 🎙️ audio-transcription-cli | A Python CLI for real-time audio-to-text transcription using LFM2-Audio-1.5B with llama.cpp |
| A Python CLI that helps you find and book plane tickets using LFM2.5-1.2B-Thinking with tool calling | |
| 🚗 audio-car-cockpit | A voice-controlled car cockpit demo combining LFM2.5-Audio-1.5B (TTS/STT) with LFM2-1.2B-Tool for real-time local inference |
| 🔊 audio-webgpu-demo | Run LFM2.5-Audio-1.5B entirely in your browser with WebGPU for speech recognition, text-to-speech, and interleaved audio/text conversation |
| 📹 vl-webgpu-demo | Real-time video captioning with LFM2.5-VL-1.6B running in-browser using WebGPU |
The LEAP Edge SDK is our native framework for running LFM2 models on mobile devices.
Written for Android (Kotlin) and iOS (Swift), the goal of the Edge SDK is to make Small Language Model deployment as easy as calling a cloud LLM API endpoint, for any app developer.
| Example | Description |
|---|---|
| LeapChat | A comprehensive chat application with real-time token streaming, persistent message history, and modern chat UI featuring message bubbles and typing indicators |
| SloganApp | Single turn generation for marketing. The UI is implemented with Android Views. |
| ShareAI | Website summary generator |
| Recipe Generator | Structured output generation with the LEAP SDK |
| Visual Language Model example | Visual Language Model example |
| Example | Description |
|---|---|
| LeapChat | A comprehensive chat application demonstrating advanced LeapSDK features including real-time streaming, conversation management, and modern UI components. |
| LeapSloganExample | A simple SwiftUI app demonstrating basic LeapSDK integration for text generation. |
| Recipe Generator | Structured output generation |
| Audio demo | A SwiftUI app demonstrating audio input and output with the LeapSDK for on-device AI inference. |
Complete end-to-end tutorials that take you from setup to deployment.
| Tutorial | Repository |
|---|---|
| Super fast and accurate image classification on edge devices |  |
| Let's build a Chess game using small and local Large Language Models |  |
Working applications that demonstrate Liquid models in action.
| Project | Repository |
|---|---|
| TranslatorLens: Building An Offline Translation Camera |  |
| Food Images Fine-tuning |  |
| Meeting Intelligence CLI |  |
| Private Doc Q&A: On-device document Q&A with RAG and voice input |  |
| Photo Triage Agent: Private photo library cleanup using LFM vision model |  |
| LFM-Scholar: Automated literature review agent capable of finding and citing papers |  |
| LFM2-KoEn-Tuning: Fine-tuned LFM2 1.2B model specialized for Korean-English translation |  |
| Chat with LEAP SDK on React Native |  |
| Private Summarizer: 100% local text summarization with multi-language support |  |
| Tiny-MoA: Running Mixture of Agents on CPU: LFM2.5 Brain (1.2B) + Multi-Agent |  |
| Date | Topic |
|---|---|
| 2025-11-06 | |
| 2025-11-27 | |
| 2025-12-26 | |
| 2026-01-22 |
Wanna participate in the next session? Join the Liquid Discord community and head to the #live-events channel!
We welcome contributions!
- Open a PR with a link to your project github repo in the
Examples built by our communitysection.