DEV Community

Gemma

Gemma is a collection of lightweight, state-of-the-art open models built from the same technology that powers our Gemini models.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Built an AI Receipt Scanner with Gemma 4 — As an SDET with No Dev Background

Gemma 4 Challenge: Build With Gemma 4 Submission

I Built an AI Receipt Scanner with Gemma 4 — As an SDET with No Dev Background

2
Comments
6 min read
Comparing Model Performance: Without MTP vs. With MTP vs. With MTP + QAT

Comparing Model Performance: Without MTP vs. With MTP vs. With MTP + QAT

Comments
8 min read
Gemma 4 and the Future of Local AI

Gemma 4 Challenge: Write about Gemma 4 Submission

Gemma 4 and the Future of Local AI

3
Comments
2 min read
This is a submission for the [Gemma 4 Challenge: Build with Gemma 4](https://dev.to/challenges/google-gemma-2026-05-06

Gemma 4 Challenge: Build With Gemma 4 Submission

This is a submission for the [Gemma 4 Challenge: Build with Gemma 4](https://dev.to/challenges/google-gemma-2026-05-06

3
Comments
2 min read
Join the Gemma 4 Challenge: $3,000 prize pool for TEN winners!

Announcing the Gemma 4 Challenge

Join the Gemma 4 Challenge: $3,000 prize pool for TEN winners!

452
Comments 105
5 min read
What I shipped during I/O 2026 week: Gemma 4 on Ollama with a five-piece safety stack

What I shipped during I/O 2026 week: Gemma 4 on Ollama with a five-piece safety stack

Comments
5 min read
No Cloud, No Cost: Build an Offline Visual AI Agent with Gemma 4

No Cloud, No Cost: Build an Offline Visual AI Agent with Gemma 4

8
Comments 1
5 min read
ECET AI Study Buddy using Gemma 4 – My First Local AI Project

Gemma 4 Challenge: Build With Gemma 4 Submission

ECET AI Study Buddy using Gemma 4 – My First Local AI Project

Comments 1
1 min read
Introducing Gemma 4 12B: a unified, encoder-free multimodal model

Introducing Gemma 4 12B: a unified, encoder-free multimodal model

40
Comments 3
4 min read
How Gemma 4's Per-Layer Embeddings Actually Work — And Why E2B Punches Above 2B

Gemma 4 Challenge: Write about Gemma 4 Submission

How Gemma 4's Per-Layer Embeddings Actually Work — And Why E2B Punches Above 2B

6
Comments
10 min read
HABIT TRACKER!

Gemma 4 Challenge: Build With Gemma 4 Submission

HABIT TRACKER!

1
Comments
1 min read
Project Log #1: I'm Building an AI Agent That Controls a Phone

Project Log #1: I'm Building an AI Agent That Controls a Phone

Comments
2 min read
dwriter: An AI-powered terminal tool that helps you record and reflect.

Gemma 4 Challenge: Build With Gemma 4 Submission

dwriter: An AI-powered terminal tool that helps you record and reflect.

2
Comments
3 min read
Gemma 4 Made Me Question Why We Still Obsess Over Huge AI Models

Gemma 4 Challenge: Write about Gemma 4 Submission

Gemma 4 Made Me Question Why We Still Obsess Over Huge AI Models

4
Comments
3 min read
Your Story: Local Gemma 4 Interactive Fiction That Remembers Your Choices

Gemma 4 Challenge: Build With Gemma 4 Submission

Your Story: Local Gemma 4 Interactive Fiction That Remembers Your Choices

31
Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.