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.
OpenAgent for Obsidian: Local-Only Grounded Research with Gemma 4

Gemma 4 Challenge: Build With Gemma 4 Submission

OpenAgent for Obsidian: Local-Only Grounded Research with Gemma 4

16
Comments
3 min read
A Day in the Life of a Local First Developer

Gemma 4 Challenge: Write about Gemma 4 Submission

A Day in the Life of a Local First Developer

4
Comments
5 min read
Anatomy of the Slopster

Gemma 4 Challenge: Write about Gemma 4 Submission

Anatomy of the Slopster

8
Comments
18 min read
I built a local document Q&A tool around Gemma 4 E4B's 128K context — five days, no RAG, no cloud

Gemma 4 Challenge: Build With Gemma 4 Submission

I built a local document Q&A tool around Gemma 4 E4B's 128K context — five days, no RAG, no cloud

40
Comments 3
7 min read
I Generated a Tableau Dashboard Using Gemma 4 — Locally, No API Key, No Cloud

I Generated a Tableau Dashboard Using Gemma 4 — Locally, No API Key, No Cloud

Comments
6 min read
My 6-year-old asks 400 questions a day. So I built him a Gemma 4 AI tutor.

Gemma 4 Challenge: Build With Gemma 4 Submission

My 6-year-old asks 400 questions a day. So I built him a Gemma 4 AI tutor.

32
Comments 3
5 min read
MCP Just Landed on Your Phone: What Google AI Edge Gallery Actually Does

Google I/O Challenge submission

MCP Just Landed on Your Phone: What Google AI Edge Gallery Actually Does

55
Comments 16
6 min read
I Got Tired of AI Black Boxes So I Built One You Can Break Into

Gemma 4 Challenge: Build With Gemma 4 Submission

I Got Tired of AI Black Boxes So I Built One You Can Break Into

6
Comments
4 min read
Local-First AI Done Right: How Gemma 4 E2B and 'Thinking Mode' Powered DiagramFlowAI

Gemma 4 Challenge: Build With Gemma 4 Submission

Local-First AI Done Right: How Gemma 4 E2B and 'Thinking Mode' Powered DiagramFlowAI

102
Comments 62
4 min read
I stress-tested Gemma 4 E4B's 128K context on a laptop GPU — recall is great, prefill is not

Gemma 4 Challenge: Write about Gemma 4 Submission

I stress-tested Gemma 4 E4B's 128K context on a laptop GPU — recall is great, prefill is not

23
Comments 4
7 min read
Adding Gemma 4 speech recognition to a .NET desktop app: the llama-server sidecar that survived

Adding Gemma 4 speech recognition to a .NET desktop app: the llama-server sidecar that survived

1
Comments
14 min read
GizmoGuard - Spy Bot (Powered by Gemma4)

Gemma 4 Challenge: Build With Gemma 4 Submission

GizmoGuard - Spy Bot (Powered by Gemma4)

20
Comments
5 min read
Aasa: The Phone That Finally Notices

Gemma 4 Challenge: Build With Gemma 4 Submission

Aasa: The Phone That Finally Notices

13
Comments
6 min read
The G Factor: Your own little music talent show 🗣️🎤

Gemma 4 Challenge: Write about Gemma 4 Submission

The G Factor: Your own little music talent show 🗣️🎤

20
Comments
7 min read
SimGemma: Democratizing STEM Education with Offline-First AI Simulations

Gemma 4 Challenge: Build With Gemma 4 Submission

SimGemma: Democratizing STEM Education with Offline-First AI Simulations

1
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.