Liquid4All/cookbook

Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK

What it solves

This repository provides a comprehensive collection of examples, tutorials, and applications designed to help developers implement Liquid AI's open-weight Liquid Foundation Models (LFMs) and the LEAP SDK across various platforms, including laptops, mobile devices, and edge hardware.

How it works

The cookbook organizes resources into several implementation paths:

  • Desktop & Mobile Apps: Provides source code for native applications (Python, Kotlin, Swift) that run LFMs locally for tasks like audio transcription, invoice parsing, and voice assistance.
  • Browser Apps: Demonstrates how to run models directly in the browser using WebGPU, ONNX Runtime Web, and WebAssembly for zero-install AI experiences.
  • Fine-Tuning: Offers Colab notebooks and scripts using frameworks like Unsloth and TRL to customize text, vision, and audio models via techniques such as SFT, DPO, and GRPO.
  • Community Projects: Curates third-party implementations ranging from RAG-based study assistants to satellite imagery analysis for wildfire prevention.

Who it’s for

It is intended for developers and AI engineers who want to deploy small, efficient language models on-device (edge AI) rather than relying solely on cloud APIs.

Highlights

  • Multi-modal Examples: Includes implementations for text, vision (VLM), and audio-to-speech models.
  • Edge Deployment: Specific guides for Apple Silicon Macs, Android, and iOS using the LEAP Edge SDK.
  • Browser-based AI: Examples of running reasoning and vision models locally via WebGPU.
  • Advanced Training: Tutorials on continued pre-training and reinforcement learning (GRPO) for verifiable tasks.

Related

  • Project
    OpenSQZ/MiniCPM-V-CookBook

    A comprehensive implementation guide and deployment cookbook for the MiniCPM series, enabling the integration of vision, speech, and text AI capabilities across edge devices and enterprise servers.

  • Project
    qualcomm/ai-hub-apps

    A collection of sample apps and tutorials for deploying machine learning models on Qualcomm devices, supporting various runtimes and Snapdragon NPU acceleration.

  • Dispatch
    LLM Inference on Edge: Running Local LLMs via React Native

    Hugging Face provides a comprehensive guide to building a privacy-focused mobile application using React Native and llama.rn to run quantized GGUF models locally on Android and iOS.

  • Project
    google-ai-edge/litert-samples

    A collection of official and community samples, model recipes, and deployment tools for LiteRT and LiteRT-LM to enable high-performance on-device machine learning.

  • Project
    google-ai-edge/gallery

    A mobile and macOS application for running open-source LLMs locally on-device, providing a private and offline environment to experience and evaluate generative AI.