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

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Ran Google's latest Gemma 4 Models on 48GB GPU. Here's What Actually Happened.

I Ran Google's latest Gemma 4 Models on 48GB GPU. Here's What Actually Happened.

6
Comments 1
6 min read
Gemma on the Edge: Building Private, Low-Cost AI Features for Real Apps

Gemma on the Edge: Building Private, Low-Cost AI Features for Real Apps

Comments
9 min read
Gemma 4 for AI Agents: Google's Best Open Model Review 2026

Gemma 4 for AI Agents: Google's Best Open Model Review 2026

1
Comments
3 min read
I Tested Every Gemma 4 Model Locally on My MacBook - What Actually Works

I Tested Every Gemma 4 Model Locally on My MacBook - What Actually Works

5
Comments 1
4 min read
How to Add Gemma 4 Models to OpenClaw (Fix Missing Model Error)

How to Add Gemma 4 Models to OpenClaw (Fix Missing Model Error)

12
Comments
7 min read
Gemma-SRE: Self-Hosted vLLM Infrastructure Agent

Gemma-SRE: Self-Hosted vLLM Infrastructure Agent

1
Comments
18 min read
Building Your First RAG System

Building Your First RAG System

9
Comments 1
3 min read
Gemini versus Gemma: Still Confused?

Gemini versus Gemma: Still Confused?

13
Comments 1
4 min read
I Trained a Tiny AI to Judge My Hacker News Feed (And You Can Too)

I Trained a Tiny AI to Judge My Hacker News Feed (And You Can Too)

7
Comments 2
2 min read
Free Academic Paper Translation with TranslateGemma

Free Academic Paper Translation with TranslateGemma

10
Comments 1
14 min read
[ Open Source Project] open-translate — Offline Translation Web Service Powered by TranslateGemma

[ Open Source Project] open-translate — Offline Translation Web Service Powered by TranslateGemma

9
Comments
3 min read
📌 DevOps Interview Buddy using n8n, Ollama, and Gemma: Completely Free (Bonus: OpenRouter)📌

📌 DevOps Interview Buddy using n8n, Ollama, and Gemma: Completely Free (Bonus: OpenRouter)📌

Comments
1 min read
[AI Agent] TPU-Based AI Agent Development: Integrating the Twinkle AI Open Source Model (gemma-3–4B-T1-it) with Google ADK Tools

[AI Agent] TPU-Based AI Agent Development: Integrating the Twinkle AI Open Source Model (gemma-3–4B-T1-it) with Google ADK Tools

14
Comments
8 min read
Hands-on with Gemma 3 on Google Cloud

Hands-on with Gemma 3 on Google Cloud

26
Comments 4
3 min read
Serverless AI: EmbeddingGemma with Cloud Run

Serverless AI: EmbeddingGemma with Cloud Run

20
Comments
7 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.