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.
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
dragon_ha_700d0d2f551032c profile

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

#devchallenge #gemmachallenge #gemma #python
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
tagzauthor profile

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

#devchallenge #gemmachallenge #gemma #cybersecurity
2
Comments
4 min read
What Gemma 4 Means for Africa

Gemma 4 Challenge: Write about Gemma 4 Submission
loktioncode profile

What Gemma 4 Means for Africa

#devchallenge #gemmachallenge #gemma #ai
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
bymfds profile

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

#devchallenge #gemmachallenge #gemma
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
mrviduus profile

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

#devchallenge #gemmachallenge #gemma #ollama
7
Comments 3
6 min read
I Built a Multi-Agent AI Tribunal with Gemma 4

Gemma 4 Challenge: Build With Gemma 4 Submission
ujja profile
ujja

I Built a Multi-Agent AI Tribunal with Gemma 4

#devchallenge #gemmachallenge #gemma #agents
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
wildeconforce profile

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

#showdev #gemma #gemmachallenge #devchallenge
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
abhishekmauryageek profile

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

#devchallenge #gemmachallenge #gemma
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
akshat_uniyal profile

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

#devchallenge #gemmachallenge #gemma
3
Comments 2
7 min read
Consensus-hardening-protocol

Gemma 4 Challenge: Build With Gemma 4 Submission
shyam_desigan_c6b74c32b3c profile

Consensus-hardening-protocol

#devchallenge #gemmachallenge #gemma
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
imjoseangel profile

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

#devchallenge #gemmachallenge #gemma
21
Comments 4
4 min read
Building a Mini Palantir on gemma4:e4b — 128K Context Lets the Graph Actually Be Graph-RAG

Gemma 4 Challenge: Build With Gemma 4 Submission
hashevolution profile

Building a Mini Palantir on gemma4:e4b — 128K Context Lets the Graph Actually Be Graph-RAG

#devchallenge #gemmachallenge #gemma
7
Comments 3
5 min read
Cinderella is in Good Hands — Building an Agentic IoT System with Gemma 4 and ASHA

Gemma 4 Challenge: Build With Gemma 4 Submission
piusoblie profile

Cinderella is in Good Hands — Building an Agentic IoT System with Gemma 4 and ASHA

#devchallenge #gemmachallenge #gemma #iot
1
Comments
5 min read
I shipped local LLM features two months ago. Production never ran them once.

Gemma 4 Challenge: Build With Gemma 4 Submission
mrviduus profile

I shipped local LLM features two months ago. Production never ran them once.

#devchallenge #gemmachallenge #gemma #ollama
10
Comments 8
13 min read
Open-Source-First: How Close Can Gemma 4 Get to Frontier Closed Models on Real Trading Bot Failure Data?

Gemma 4 Challenge: Write about Gemma 4 Submission
wildeconforce profile

Open-Source-First: How Close Can Gemma 4 Get to Frontier Closed Models on Real Trading Bot Failure Data?

#showdev #gemma #gemmachallenge #devchallenge
2
Comments
12 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.