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 GHOST — an AI agent that actually fixes your slow laptop using Gemma 4 locally

Gemma 4 Challenge: Build With Gemma 4 Submission

I built GHOST — an AI agent that actually fixes your slow laptop using Gemma 4 locally

6
Comments 4
7 min read
No Internet? No Problem. How I Built a Crop Disease Detector for Rural India

Gemma 4 Challenge: Build With Gemma 4 Submission

No Internet? No Problem. How I Built a Crop Disease Detector for Rural India

4
Comments 4
3 min read
I Ran Gemma 4 on a $7/Month Server and Built an AI-Powered News Monitor That Costs $0 to Operate

Gemma 4 Challenge: Build With Gemma 4 Submission

I Ran Gemma 4 on a $7/Month Server and Built an AI-Powered News Monitor That Costs $0 to Operate

3
Comments 2
12 min read
The End of Renting Intelligence? Why Gemma 4 Makes Local AI Feel Viable

Gemma 4 Challenge: Write about Gemma 4 Submission

The End of Renting Intelligence? Why Gemma 4 Makes Local AI Feel Viable

9
Comments 1
5 min read
The model isn’t the hard part: the data pipeline I built to teach Gemma 4 E2B to read Indian GST invoices.

Gemma 4 Challenge: Write about Gemma 4 Submission

The model isn’t the hard part: the data pipeline I built to teach Gemma 4 E2B to read Indian GST invoices.

1
Comments 1
7 min read
Open-Source Intelligence: Building with Gemma and MCP

Open-Source Intelligence: Building with Gemma and MCP

2
Comments
2 min read
🚀 Gemma Doc Pro: Privacy-First Codebase Intelligence Dashboard

Gemma 4 Challenge: Build With Gemma 4 Submission

🚀 Gemma Doc Pro: Privacy-First Codebase Intelligence Dashboard

11
Comments
4 min read
I Tested Gemma 4 E4B vs 31B on 50 Real Student Career Queries — The Results Surprised Me

Gemma 4 Challenge: Write about Gemma 4 Submission

I Tested Gemma 4 E4B vs 31B on 50 Real Student Career Queries — The Results Surprised Me

7
Comments 1
8 min read
Gemma 4 vs Claude vs Llama: Which Model Wins for Devs

Gemma 4 Challenge: Write about Gemma 4 Submission

Gemma 4 vs Claude vs Llama: Which Model Wins for Devs

164
Comments 58
8 min read
I Stopped Chunking My Logs. Then Gemma 4's 128K Context Found What I'd Missed for Weeks

Gemma 4 Challenge: Write about Gemma 4 Submission

I Stopped Chunking My Logs. Then Gemma 4's 128K Context Found What I'd Missed for Weeks

5
Comments 1
8 min read
I Ran Google's Gemma 4 on a 10-Year-Old Laptop With No GPU. Here Is What I Found.

Gemma 4 Challenge: Write about Gemma 4 Submission

I Ran Google's Gemma 4 on a 10-Year-Old Laptop With No GPU. Here Is What I Found.

3
Comments 1
8 min read
Gemma 4 and the Architecture of On-Device AI

Gemma 4 and the Architecture of On-Device AI

Comments
3 min read
Making Gemma 4 (e2b) production-safe with five tiny libraries

Gemma 4 Challenge: Build With Gemma 4 Submission

Making Gemma 4 (e2b) production-safe with five tiny libraries

4
Comments
5 min read
Gemma 4: From Raspberry Pi to Research Workstation — One Architecture, No Quality Compromise

Gemma 4 Challenge: Write about Gemma 4 Submission

Gemma 4: From Raspberry Pi to Research Workstation — One Architecture, No Quality Compromise

12
Comments
13 min read
GemmaDiff: I Built a Local AI Code Reviewer with Gemma 4 That Never Sends Your Code to the Cloud

Gemma 4 Challenge: Build With Gemma 4 Submission

GemmaDiff: I Built a Local AI Code Reviewer with Gemma 4 That Never Sends Your Code to the Cloud

7
Comments 1
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.