Cookbook

<div align="center"> <img src="https://github.com/user-attachments/assets/e0f42ac6-822f-4b7b-a0ae-07b2a619258d" alt="Liquid AI" style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;" /> <div style="display: flex; justify-content: center; gap: 0.5em;"> <a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> • <a href="https://docs.liquid.ai/lfm"><strong>Documentation</strong></a> • <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a> </div> <br/> <a href="https://discord.com/invite/liquid-ai"><img src="https://img.shields.io/discord/1385439864920739850?style=for-the-badge&logo=discord&logoColor=white&label=Discord&color=5865F2" alt="Join Discord"></a> </div> </br>

Examples, tutorials, and applications to help you build with our open-weight LFMs and the LEAP SDK on laptops, mobile, and edge devices.

Contents

• Desktop Apps
• Browser Apps
• Mobile Apps (Android / iOS)
• Fine-Tuning Notebooks
• Third-Party Apps Powered by LFM
• Community Projects
• Technical Deep Dives
• Contributing
• Support

🖥️ Desktop Apps

Python and CLI applications for running LFM models on your laptop or desktop machine.

| Name | Description | Link | |------|-------------|------| | Invoice Parser | Extract structured data from invoice images using LFM2-VL-3B | Code | | Audio Transcription CLI | Real-time audio-to-text transcription using LFM2-Audio-1.5B with llama.cpp | Code | | Flight Search Assistant | Find and book plane tickets using LFM2.5-1.2B-Thinking with tool calling | Code | | Audio Car Cockpit | Voice-controlled car cockpit demo combining LFM2.5-Audio-1.5B with LFM2-1.2B-Tool | Code | | LocalCowork | On-device AI agent for file ops, security scanning, OCR, and more, powered by LFM2-24B-A2B | Code | | Home Assistant | Local home assistant with tool calling, benchmarking, and fine-tuning pipeline using LFM2-350M and LFM2.5-1.2B | Code |

🌐 Browser Apps

Zero-install applications running LFM models directly in the browser via WebGPU and ONNX Runtime Web.

| Name | Description | Link | |------|-------------|------| | Tool Calling | Run LFM2 entirely in your browser with WebGPU for in-browser tool calling | Code | Demo | | Voice Assistant | Run LFM2.5-Audio-1.5B entirely in your browser for speech recognition, TTS, and conversation | Code | Demo | | Live Video Captioning | Real-time video captioning with LFM2.5-VL-1.6B running in-browser using WebGPU | Code | Demo | | Chain-of-Thought Reasoning | Run LFM2.5-1.2B-Thinking entirely in your browser with WebGPU for on-device chain-of-thought reasoning | Code | Demo | | Hand & Voice Racer | Browser driving game controlled by hand gestures (MediaPipe) and voice commands (LFM2.5-Audio-1.5B), running fully local | Code |

📱 Mobile Apps

Native examples for deploying LFM2 models on iOS and Android using the LEAP Edge SDK. 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.

Android

| Name | Description | Link | |------|-------------|------| | LeapChat | Chat app with real-time streaming, persistent history, and modern UI | Code | | LeapAudioDemo | Audio input and output with LFM2.5-Audio-1.5B for on-device AI inference | Code | | LeapKoogAgent | Integration with Koog framework for AI agent functionality | Code | | SloganApp | Single turn marketing slogan generation with Android Views | Code | | ShareAI | Website summary generator | Code | | Recipe Generator | Structured output generation with the LEAP SDK | Code | | VLM Example | Visual Language Model integration | Code |

iOS

| Name | Description | Link | |------|-------------|------| | LeapChat | Chat app with real-time streaming, conversation management, and SwiftUI | Code | | LeapSloganExample | Basic LeapSDK integration for text generation in SwiftUI | Code | | Recipe Generator | Structured output generation | Code | | Audio Demo | Audio input/output with LeapSDK for on-device AI inference | Code |

🎯 Fine-Tuning Notebooks

Colab notebooks and Python scripts for customizing LFM models with your own data.

| Name | Description | Link | |------|-------------|------| | Supervised Fine-Tuning (SFT) | | | | SFT with Unsloth | Memory-efficient SFT using Unsloth with LoRA for 2x faster training | Notebook | | SFT with TRL | Supervised fine-tuning using Hugging Face TRL library with parameter-efficient LoRA | Notebook | | Reinforcement Learning | | | | GRPO with Unsloth | Train reasoning models using Group Relative Policy Optimization for verifiable tasks | Notebook | | GRPO with TRL | Train reasoning models using Group Relative Policy Optimization with rule-based rewards | Notebook | | Continued Pre-Training (CPT) | | | | CPT for Translation | Adapt models to specific languages or translation domains using domain data | Notebook | | CPT for Text Completion | Teach models domain-specific knowledge and creative writing styles | Notebook | | Vision-Language Models | | | | VLM SFT with Unsloth | Supervised fine-tuning for LFM2-VL models on custom image-text datasets | Notebook |

Third-Party Apps Powered by LFM

Production and open-source applications that support LFM models as an inference backend, among other providers.

| Name | Description | Link | |------|-------------|------| | DeepCamera | Open-source AI camera system for local vision intelligence with facial recognition, person re-ID, and edge deployment on Jetson and Raspberry Pi | Code | | Osaurus | Native macOS AI harness for managing agents, memory, tools, and identity locally, with support for LFM models via MLX on Apple Silicon | Code |

🌟 Community Projects

Open-source projects built by the community showcasing LFMs with real use cases.

Featured

| Name | Description | Link | |------|-------------|------| | Image Classification on Edge | End-to-end tutorial covering fine-tuning and deployment for super fast and accurate image classification using local VLMs | Code | | Chess Game with Small LMs | End-to-end tutorial covering fine-tuning and deployment to build a Chess game using Small Language Models | Code | | Private Doc Q&A | On-device document Q&A with RAG and voice input | Code | | LFM2.5 Mobile Actions | LoRA fine-tuned LFM2.5-1.2B that translates natural language into Android OS function calls for on-device mobile action recognition | Code | | Photo Triage Agent | Private photo library cleanup using LFM vision model | Code | | Tiny-MoA | Mixture of Agents on CPU with LFM2.5 Brain (1.2B) | Code | | barq-web-rag | Browser-based RAG app for document Q&A with LFM2.5-1.2B-Thinking running fully local via WebGPU | Code | | LFM-Scholar | Automated literature review agent for finding and citing papers | Code |

More

| Name | Description | Link | |------|-------------|------| | Private Summarizer | 100% local text summarization with multi-language support | Code | | TranslatorLens | Offline translation camera for real-time tex