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.
Vellum — a private, on‑device screenshot assistant powered by Gemma 4

Gemma 4 Challenge: Build With Gemma 4 Submission

Vellum — a private, on‑device screenshot assistant powered by Gemma 4

5
Comments 1
5 min read
Genie: Building a Privacy-First Autonomous Agent That Controls Your Phone, Entirely Offline

Gemma 4 Challenge: Build With Gemma 4 Submission

Genie: Building a Privacy-First Autonomous Agent That Controls Your Phone, Entirely Offline

20
Comments 2
10 min read
Three Generations Built This Robot. Gemma 4 Taught Him to Listen.

Gemma 4 Challenge: Build With Gemma 4 Submission

Three Generations Built This Robot. Gemma 4 Taught Him to Listen.

16
Comments 7
7 min read
Gaslighting Gemma 4: Can Open-Weight Reasoning Models Withstand a Confident Liar?

Gemma 4 Challenge: Write about Gemma 4 Submission

Gaslighting Gemma 4: Can Open-Weight Reasoning Models Withstand a Confident Liar?

Comments
4 min read
What Gemma 4 Doesn't Know About Cameroon — and What That Taught Me About Building AI for the Real World

Gemma 4 Challenge: Write about Gemma 4 Submission

What Gemma 4 Doesn't Know About Cameroon — and What That Taught Me About Building AI for the Real World

5
Comments
5 min read
Gemma Mentor AI

Gemma 4 Challenge: Build With Gemma 4 Submission

Gemma Mentor AI

5
Comments
5 min read
How Gemma 4 Became the Cognitive Core of a Cinematic AI Tutoring System. (Gemma4 understands and speaks your language.)

Gemma 4 Challenge: Build With Gemma 4 Submission

How Gemma 4 Became the Cognitive Core of a Cinematic AI Tutoring System. (Gemma4 understands and speaks your language.)

4
Comments
5 min read
Off the Grid: How GEMMA 4 Unlocks Private, Local AI

Gemma 4 Challenge: Write about Gemma 4 Submission

Off the Grid: How GEMMA 4 Unlocks Private, Local AI

2
Comments
5 min read
I built a real-time ASL interpreter for the Gemma4 challenge, no cloud needed

Gemma 4 Challenge: Build With Gemma 4 Submission

I built a real-time ASL interpreter for the Gemma4 challenge, no cloud needed

19
Comments 2
4 min read
Agent Surface Map: Gemma 4 review before you install an MCP

Gemma 4 Challenge: Build With Gemma 4 Submission

Agent Surface Map: Gemma 4 review before you install an MCP

2
Comments
4 min read
We Didn't Ask for AI That Does Tasks. We Asked for AI That Remembers.

Gemma 4 Challenge: Write about Gemma 4 Submission

We Didn't Ask for AI That Does Tasks. We Asked for AI That Remembers.

2
Comments
4 min read
Beyond the Hardware Barrier: Why Gemma 4 is a Game-Changer for Every Developer

Gemma 4 Challenge: Write about Gemma 4 Submission

Beyond the Hardware Barrier: Why Gemma 4 is a Game-Changer for Every Developer

2
Comments 1
5 min read
I Turned Any GitHub Repo Into a Playable Dungeon: Gemma 4 Finds Real Bugs and Turns Them Into Monsters

Gemma 4 Challenge: Build With Gemma 4 Submission

I Turned Any GitHub Repo Into a Playable Dungeon: Gemma 4 Finds Real Bugs and Turns Them Into Monsters

6
Comments 2
6 min read
Self-Hosting Gemma 4 for Production Automation Revealed Two Ollama Bugs

Gemma 4 Challenge: Build With Gemma 4 Submission

Self-Hosting Gemma 4 for Production Automation Revealed Two Ollama Bugs

10
Comments 7
9 min read
Shipping on Gemma 4: chain-of-thought leakage, MoE-vs-Dense, and on-device pragmatism

Gemma 4 Challenge: Write about Gemma 4 Submission

Shipping on Gemma 4: chain-of-thought leakage, MoE-vs-Dense, and on-device pragmatism

2
Comments
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.