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.
Agent Factory Recap: How Gemma 4 Taught Itself Physics

Agent Factory Recap: How Gemma 4 Taught Itself Physics

14
Comments 4
5 min read
The Local Model That Doesn't Sleep: Gemma 4 + MTP as a Marathon Engine

Gemma 4 Challenge: Write about Gemma 4 Submission

The Local Model That Doesn't Sleep: Gemma 4 + MTP as a Marathon Engine

23
Comments 11
18 min read
I Built a Space App That Gives You Real-Time Planetary Data — Powered by Gemma 4, No Backend

Gemma 4 Challenge: Build With Gemma 4 Submission

I Built a Space App That Gives You Real-Time Planetary Data — Powered by Gemma 4, No Backend

24
Comments 10
8 min read
Gemma 4 E4B on Mac Mini M2: Real Benchmarks for a Companion Robot

Gemma 4 E4B on Mac Mini M2: Real Benchmarks for a Companion Robot

Comments
4 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
I Built an IoT Forensic Investigation Simulator Powered by Gemma 4 — Paste Any Incident, Get a Full Case with Evidence, Decisions, and a Forensic Report

Gemma 4 Challenge: Build With Gemma 4 Submission

I Built an IoT Forensic Investigation Simulator Powered by Gemma 4 — Paste Any Incident, Get a Full Case with Evidence, Decisions, and a Forensic Report

2
Comments
4 min read
What Gemma 4 Means for Africa

Gemma 4 Challenge: Write about Gemma 4 Submission

What Gemma 4 Means for Africa

6
Comments
3 min read
Coding in the Dark: How Local Gemma 4 Saved My Python Progress During Ukrainian Blackouts

Gemma 4 Challenge: Write about Gemma 4 Submission

Coding in the Dark: How Local Gemma 4 Saved My Python Progress During Ukrainian Blackouts

4
Comments 2
3 min read
I put Ollama on a 4 GB mobile GPU and got 2.5 — here's the VRAM math

Gemma 4 Challenge: Build With Gemma 4 Submission

I put Ollama on a 4 GB mobile GPU and got 2.5 — here's the VRAM math

7
Comments 3
6 min read
I Built a Multi-Agent AI Tribunal with Gemma 4

Gemma 4 Challenge: Build With Gemma 4 Submission

I Built a Multi-Agent AI Tribunal with Gemma 4

22
Comments 6
8 min read
I Ran a 7,500-Token Architecture Spec Through 4 Models. The Cheapest One Caught Everything the Flagship Did.

Gemma 4 Challenge: Write about Gemma 4 Submission

I Ran a 7,500-Token Architecture Spec Through 4 Models. The Cheapest One Caught Everything the Flagship Did.

Comments
11 min read
Intentional Model Selection — How to Actually Choose the Right Gemma 4 Variant for Your Workload

Gemma 4 Challenge: Write about Gemma 4 Submission

Intentional Model Selection — How to Actually Choose the Right Gemma 4 Variant for Your Workload

6
Comments 3
8 min read
BugTheatre AI: Turning Screenshots, Logs, and Stack Traces Into Debugging Case Files with Gemma 4

Gemma 4 Challenge: Build With Gemma 4 Submission

BugTheatre AI: Turning Screenshots, Logs, and Stack Traces Into Debugging Case Files with Gemma 4

3
Comments 2
7 min read
Consensus-hardening-protocol

Gemma 4 Challenge: Build With Gemma 4 Submission

Consensus-hardening-protocol

3
Comments
6 min read
I Grounded Gemma 4 in 118,000 Real Stars — Here's What It Can Do

Gemma 4 Challenge: Build With Gemma 4 Submission

I Grounded Gemma 4 in 118,000 Real Stars — Here's What It Can Do

21
Comments 4
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.