\n
\n Local AI is having a moment, and we want you to be part of it!<\/p>\n
Running through May 24, the Gemma 4 Challenge invites you to explore open models. With the release of Gemma 4, Google’s most capable open model family yet, we now have access to native multimodal capabilities, advanced reasoning, a 128K context window, and models that range from running on a Raspberry Pi, to phones, to powering large-scale deployments.<\/p>\n
Whether you love to build or love to write, there’s a prompt for you and a $3,000 prize pool up for grabs!<\/p>\n
Read on to learn more.<\/p>\n
Our Prompts<\/p>\n
Build With Gemma 4<\/p>\n
Your mandate is to build something useful or creative with any Gemma 4 model. The scope is wide open \u2014 you can build anything from an IoT integration to a multimodal tool to a long-context reasoning app. What matters is that Gemma 4 is doing real work at the heart of your project.\u00a0<\/p>\n
Build With Gemma 4 Submission Template<\/p>\n
\u00a0<\/p>\n
The most compelling submissions will make a clear case for why you chose the model you did and what that model unlocked.<\/p>\n
Write About Gemma 4<\/p>\n
Your mandate is to publish a post about Gemma 4 that educates, inspires, or sparks curiosity. There’s no single right format \u2014 what matters is that your post offers something genuine and useful to the community.<\/p>\n
Not sure what to write about? Here are some ideas:<\/p>\n
How-to guide: Walk through setting up and running a Gemma 4 model locally, fine-tuning it for a specific task, or integrating it into a real project<\/p>\n
Comparison piece: Break down the three Gemma 4 model variants and help readers decide which one is right for their use case<\/p>\n
Personal essay or opinion piece: Share your experience building with Gemma 4, or make a case for something \u2014 what does a model this capable running locally mean for the future of AI?<\/p>\n
Deep technical breakdown: Explore a specific capability like multimodal input, the 128K context window, or reasoning mode<\/p>\n
\u00a0<\/p>\n
Write About Gemma 4 Submission Template<\/p>\n
\u00a0<\/p>\n
Need inspiration? Check out how Google’s own team fine-tuned Gemma 4 with Cloud Run Jobs. That\u2019s the kind of hands-on, shareable knowledge is exactly what we’re looking for.<\/p>\n
Note: If you are primarily showing off a project, please submit to the Build with Gemma 4 prompt instead! Each submission is only allowed to be eligible for one of the two categories.<\/p>\n
Which Model Is Right for You? \ud83e\udd14<\/p>\n
Gemma 4 model family spans three distinct architectures tailored for specific hardware requirements:<\/p>\n
Small Sizes: 2B and 4B effective parameter models built for ultra-mobile, edge, and browser deployment (e.g., Pixel).<\/p>\n
Dense: A powerful 31B parameter dense model that bridges the gap between server-grade performance and local execution.<\/p>\n
Mixture-of-Experts: A highly efficient 26B MoE model designed for high-throughput, advanced reasoning.<\/p>\n
No matter which you choose, judges will be looking for intentional model selection \u2014 show us why your model was the right tool for the job.<\/p>\n
Prizes \ud83c\udfc6<\/p>\n
Five winners from the \u201cBuild with Gemma 4\u201d prompt will receive:<\/p>\n
$500 USD cash prize<\/p>\n
DEV++ Membership
\nExclusive DEV Badge<\/p>\n
Five winners from the \u201cWrite About Gemma 4\u201d prompt will receive:<\/p>\n
$100 USD cash prize<\/p>\n
DEV++ Membership
\nExclusive DEV Badge<\/p>\n
All participants with a valid submission will receive a completion badge on their DEV profile.<\/p>\n
Judging Criteria<\/p>\n
Build With Gemma 4 submissions will be evaluated for:<\/p>\n
Intentional and effective use of the chosen Gemma 4 model
\nTechnical implementation and code quality
\nCreativity and originality
\nUsability and user experience<\/p>\n
Write About Gemma 4 submissions will be evaluated for:<\/p>\n
Clarity and depth of explanation
\nOriginality of perspective or insight
\nPractical value to the community
\nQuality of writing<\/p>\n
Getting Started With Gemma 4 \ud83d\ude80<\/p>\n
Gemma 4 is open \u2014 you have several ways to get started, including completely free options:<\/p>\n
Gemini API via Google AI Studio: Access Gemma 4 through the Gemini API. <\/p>\n
Run locally (free, no credit card required): Download any Gemma 4 model directly from Hugging Face or Kaggle. The E2B model runs on high-end phones \u2014 or even a Raspberry Pi 5.<\/p>\n
OpenRouter (free tier available): Access Gemma 4 31B via OpenRouter’s free tier \u2014 no credit card required.<\/p>\n
Important Dates<\/p>\n
May 6: Gemma 4 Challenge begins!<\/p>\n
May 24: Submissions due at 11:59 PM PDT<\/p>\n
June 4: Winners Announced<\/p>\n
We can’t wait to see what you build and write! Questions about the challenge? Drop them in the comments below.<\/p>\n
Good luck and happy coding!<\/p>\n