# google-gemma/cookbook

A collection of guides and examples for the Gemma open models from Google.

Repository: https://github.com/google-gemma/cookbook
Canonical: https://ross.abutalabs.com/products/google-gemma-cookbook
Homepage: https://ai.google.dev/gemma/
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: codegemma, gemma, paligemma, recurrentgemma
Last push: 2026-08-19T04:00:06+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 59
- inputs: {"age_days": 829, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3984, forks 658 (observed 2026-08-28T04:08:31.711945+00:00)

## What it is
A collection of guides, tutorials, and example notebooks for Google's Gemma family of open models, including variants like CodeGemma, MedGemma, and PaliGemma. It provides tested Jupyter notebooks, full-stack demo apps, and responsible AI resources for building with Gemma.

## Use cases
- learn how to run Gemma models locally
- fine-tune Gemma for a custom task
- build a chatbot with Gemma
- use CodeGemma for code generation
- run Gemma on low-resource devices
- explore multimodal examples with PaliGemma
- get started with Google open LLMs

## When to choose
- you want official, tested notebooks and guides for Gemma models
- you need examples spanning text, code, medical, and multimodal Gemma variants
- you are learning to deploy or fine-tune Gemma on cloud or edge devices

## When to avoid
- you need a production-ready library or API rather than example notebooks
- you are working with non-Gemma models like Llama or Mistral
- you need guaranteed accuracy, since examples may reflect model hallucinations

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, llm-inference, prompt-engineering, rag, developer-tools
- domain: large-language-models, artificial-intelligence, tutorials
- platform: python, cross-platform
- tags: gemma, google-deepmind, jupyter-notebooks, open-models, fine-tuning, codegemma, medgemma, multimodal, natural-language-processing, gpu

## Member repositories
- google-gemma/cookbook (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:31.711945+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 2026-08-29T18:24:15.317847+00:00, confidence not recorded.
  - readme: https://github.com/google-gemma/cookbook (fetched 2026-08-28T04:08:31.711945+00:00, sha 9f1b07777e25)
  - homepage: https://ai.google.dev/gemma/ (fetched 2026-08-29T09:17:34.484627+00:00, sha 458fc3b379e2)
  - site_page: https://deepmind.google/about (fetched 2026-08-29T09:17:34.493769+00:00, sha ae485140138c)
- Data as of 2026-08-30T08:39:29.467469+00:00.