# Liquid4All/cookbook

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

Repository: https://github.com/Liquid4All/cookbook
Canonical: https://ross.abutalabs.com/products/liquid4all-cookbook
Homepage: https://docs.liquid.ai/
Language: Jupyter Notebook
License Family: other
Topics: android, edge, ios, language-model, laptop, language-models
Last push: 2026-08-12T14:00:15+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 23
- inputs: {"age_days": 334, "days_push": 21, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2418, forks 377 (observed 2026-08-28T04:06:50.430888+00:00)

## What it is
A collection of examples, end-to-end tutorials, and demo applications built with Liquid AI's open-weight Liquid Foundation Models (LFM) and the LEAP SDK. It covers desktop, browser, and mobile (Android/iOS) apps, plus fine-tuning workflows for running small language, vision, and audio models on laptops and edge devices.

## Use cases
- run small language models locally on a laptop
- build an on-device voice assistant for mac or mobile
- parse invoice images with a vision-language model
- transcribe audio to text offline
- fine-tune LFM models for a custom task
- deploy LLMs on android or ios edge devices
- build a local AI agent with tool calling
- run a vision-language model chat app on-device

## When to choose
- you want working example code and tutorials for Liquid AI LFM models
- you need to deploy small LLMs on mobile, laptop, or edge hardware
- you want reference apps for on-device audio, vision, or agent use cases
- you are learning to fine-tune LFMs with LEAP Finetune, TRL, or Unsloth

## When to avoid
- you need a production-ready library or SDK rather than example code
- you use models from other providers with no interest in LFM/LEAP
- you need large-scale GPU serving examples rather than on-device inference
- you require a licensed, stable dependency for a commercial product (repo has no license)

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, machine-learning, speech-recognition, ocr, chatbot, agent-framework
- domain: large-language-models, artificial-intelligence, mobile-development, developer-tools, tutorials
- platform: windows, python, cross-platform, browser
- tags: lfm, leap-sdk, on-device-ai, edge-ai, fine-tuning, jupyter-notebooks, liquid-ai, example-apps, android, ios, macos, linux

## Member repositories
- Liquid4All/cookbook (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:50.430888+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:33:06.567766+00:00, confidence not recorded.
  - readme: https://github.com/Liquid4All/cookbook (fetched 2026-08-28T04:06:50.430888+00:00, sha fe925f8ebb75)
  - homepage: https://docs.liquid.ai/ (fetched 2026-08-29T10:13:34.777380+00:00, sha 2a20f8ba6011)
  - site_page: https://docs.liquid.ai/lfm/help/faqs (fetched 2026-08-29T10:13:34.783082+00:00, sha 9c572c96ba4b)
  - site_page: https://docs.liquid.ai/lfm/help/contributing (fetched 2026-08-29T10:13:34.784867+00:00, sha 28680f017a49)
- Data as of 2026-08-30T08:39:29.467469+00:00.