Liquid4All/cookbook

Try LFM • Documentation • LEAP

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 Examples
• Guides
• 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 LFM2.5-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 | | Voice Assistant for Mac | On-device voice assistant for Apple Silicon Macs using LFM2.5-Audio-1.5B and the LEAP SDK | Code | | Vision Assistant for Mac | On-device visual language model chat for Apple Silicon Macs using the LEAP SDK | 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 | | Road Decider | Pixel-art survival racer where Liquid's d1 decision model dodges traffic against Jev or a human player | Code | | LEAP Voice Assistant | On-device voice assistant running in the browser via WebAssembly using the LEAP SDK | 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 | | Voice Assistant | 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 | | Voice Assistant | Audio input and output with LFM2.5-Audio-1.5B for on-device AI inference | Code | | Vision Assistant | Visual language model chat on iOS using the LEAP SDK | Code | | Telco Triage | Edge-first home internet support assistant with on-device LFM routing, local tools, and cloud-assist handoff | Code |

🎯 Fine-Tuning Examples

We recommend fine-tuning LFM2.5 for your specific use case to achieve the best results. Below you'll find Colab notebooks and Python scripts for customizing LFM models with your own data.

| Name | Framework | Description | Link | |------|-----------|-------------|------| | Text Models | | | | | Continued Pre-Training (CPT) for text completion | Unsloth (Docs) | Teach models domain-specific knowledge and creative writing styles | Notebook | | Continued Pre-Training (CPT) for translation | Unsloth (Docs) | Adapt models to specific languages or translation domains using domain data | Notebook | | Supervised Fine-Tuning (SFT) | Unsloth (Docs) | Memory-efficient SFT using Unsloth with LoRA for 2x faster training | Notebook | | Supervised Fine-Tuning (SFT) | TRL (Docs) | Supervised fine-tuning using Hugging Face TRL library with parameter-efficient LoRA | Notebook | | Supervised Fine-Tuning (SFT) for Mixture-of-Experts | Halo (Docs) | Supervised fine-tuning of LFM2.5-8B-A1B with two-way expert parallelism using Halo | Notebook | | Direct Preference Optimization (DPO) | TRL (Docs) | Align models with human preferences using direct preference optimization with LoRA | Notebook | | Antidoom Training (FTPO) | TRL (Docs) | Eliminate doom loops with final token preference optimization (FTPO) using the Antidoom pipeline | Notebook | | Group Relative Policy Optimization (GRPO) | TRL (Docs) | Train reasoning models using Group Relative Policy Optimization with rule-based rewards | Notebook | | Group Relative Policy Optimization (GRPO) | TRL (Docs) | Train a 350M model for better structured output compliance | Notebook | | Group Relative Policy Optimization (GRPO) | Unsloth (Docs) | Train reasoning models using Group Relative Policy Optimization for verifiable tasks | Notebook | | Decision Models | | | | | Supervised Fine-Tuning (SFT) | TRL (Docs) | Learn how to fine-tune a decision model (d1-3B) on your own labels with LoRA, using intent classification on Banking77 as the example | Notebook | | Supervised Fine-Tuning (SFT) | Unsloth (Docs) | Learn how to fine-tune a decision model (d1-3B) on your own labels with Unsloth and LoRA, using intent classification on Banking77 as the example | Notebook | | Vision Models | | | | | Supervised Fine-Tuning (SFT) | Unsloth (Docs) | Supervised fine-tuning for LFM2-VL models on custom image-text datasets | Notebook | | Supervised Fine-Tuning (SFT) | TRL (Docs) | Supervised fine-tuning for LFM2.5-VL models using TRL with parameter-efficient LoRA | Notebook | | Supervised Fine-Tuning (SFT) | Halo (Docs) | Supervised fine-tuning for LFM2.5-VL-3B on CPPE-5 for object detection | Notebook | | Satellite VLM Fine-Tuning | leap-finetune | Fine-tune LFM2.5-VL-450M on satellite imagery for VQA, grounding, and captioning using Modal | Code | | Wildfire Prevention | leap-finetune | Build a wildfire risk detection system using LFM2.5-VL-450M and Sentinel-2 satellite imagery, with fine-tuning and on-device inference | Code | | Audio Models | | | | | LFM2.5-Audio Fine-Tuning | liquid-audio | Fine-tune LFM2.5-Audio-1.5B on the OHF-Voice dataset to map speech directly to Home Assistant function calls, with on-device GGUF inference | Code | | Encoder Models | | | | | Document Classification | HF Transformers | Fine-tune LFM2.5-Encoder for custom long-document multi-label classification | Code |

📓 Guides

Notebooks walking through the capabilities of specific LFM models with Hugging Face Transformers.

| Name | Description | Link | |------|-------------|------| | Vision Capabilities | Image description, visual question answering, multi-image comparison, text reading, object localization, and tool calling with LFM2.5-VL | Notebook | | Longevity Models | Interpret clinical, DNA methylation, transcriptomic, proteomic, and genetic aging data with LFM2-1.2B-Longevity and LFM2-2.6B-Longevity | 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 | | SelfLink | Native iOS privacy-first journaling app | Website |

🌟 Community Projects

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

Fine-tuning

| Name | Description | Link | |------|-------------|------| | 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 | | Food Images Fine-tuning | Fine-tune LFM models on food image datasets | Code | | LFM2-KoEn-Tuning | Fine-tuned LFM2 1.2B for Korean-English translation | Code | | SFT + DPO Fine-tuning | Teaching a 1.2B model to be a grumpy Italian chef: SFT + DPO fine-tuning with Unsloth | Code | | LFM2-2.6B Mr. Tic Tac Toe | Fine-tune LFM2-2.6B with reinforcement learning to play tic-tac-toe | Code |

Deployment

| Name | Description | Link | |------|-------------|------| | LFM-2.5 Thinking on Web | Run LFM2.5-1.2B reasoning model locally in the browser via WebGPU and Transformers.js | Code | | LFM-2.5 JP on Web | Run LFM2.5-1.2B Japanese model locally in the browser via WebGPU and Transformers.js | Code | | barq-web-rag | Browser-based RAG app for document Q&A with LFM2.5-1.2B-Thinking running fully local via WebGPU | Code | | Tauri Plugin LEAP AI | Tauri plugin to integrate LEAP and Liquid LFMs into desktop and mobile apps | Crate | | Chat with LEAP SDK | LEAP SDK integration for React Native | Code |

End-to-End Projects

| Name | Description | Link | |------|-------------|------| | Image Classification on Edge | Fine-tune and deploy a local VLM for fast, accurate image classification on edge devices | Code | | Chess Game with Small LMs | Fine-tune and deploy a small language model to play chess | Code | | Private Doc Q&A | On-device document Q&A with RAG and voice input | 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 | | LFM-Scholar | Automated literature review agent for finding and citing papers | Code | | Private Summarizer | 100% local text summarization with multi-language support | Code | | TranslatorLens | Offline translation camera for real-time text translation | Code | | Meeting Intelligence CLI | CLI tool for meeting transcription and analysis | Code | | grosme | CLI grocery assistant that finds Walmart product matches using an LFM-2.5 tool-calling agent via Ollama | Code | | Discord Moderator | Use LFM2.5-1.2B to screen messages for suspicious content | Code | | BookMind | Offline RAG study assistant for asking questions and generating exercises from PDF textbooks, powered by LFM2-2.6B | Code | | Liquid-CLI | Fine-tune and run Liquid AI's LFM2-8B-A1B as a local terminal agent | Code | | LFM Podcast Studio | Turn any PDF into a two-host podcast episode locally using LFM2.5-Audio TTS via llama.cpp | Code | | GalamseyWatch | Two-layer agentic Earth observation over Sentinel-2 imagery for illegal mining detection in Ghana, powered by LFM2.5-VL-450M and LFM2-2.6B | Code | | Liquid Lens | Detects water anomalies in orbit by combining fast spectral filtering with conditional LFM2.5-VL visual insights on the SimSat orbital simulator | Code |

🕐 Technical Deep Dives

Recorded sessions (~60 minutes) covering advanced topics and hands-on implementations.

| Date | Topic | Link | |------|-------|------| | 2025-11-06 | Fine-tuning LFM2-VL for image classification | Video | | 2025-11-27 | Building a 100% local Audio-to-Speech CLI with LFM2-Audio | Video | | 2025-12-26 | Fine-tuning LFM2-350M for browser control with GRPO and OpenEnv | Video | | 2026-01-22 | Local video-captioning with LFM2.5-VL-1.6B and WebGPU | Video | | 2026-03-05 | Build your own local AI coding assistant | Video | | 2026-04-22 | Let's build a wildfire detection system with a Vision Language Model and satellite images | Video | | 2026-06-12 | Building on-device voice agents | Video |

Join the next session! Head to the #live-events channel on Discord.

Contributing

We welcome contributions! Open a PR with a link to your project GitHub repo in the Community Projects section.

Support

• 📖 Liquid AI Documentation
• 💬 Join our community on Discord