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.
Gemma4 Speculative Decoding with n-gram

Gemma 4 Challenge: Write about Gemma 4 Submission
xbill profile

Gemma4 Speculative Decoding with n-gram

#devchallenge #gemmachallenge #gemma #ai
11
Comments
2 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
23
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
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
8
Comments 4
5 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
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
Run Gemma 4 on Your Laptop — A Hands-On Guide to Google's Latest Open Multimodal LLM
jubinsoni profile

Run Gemma 4 on Your Laptop — A Hands-On Guide to Google's Latest Open Multimodal LLM

#ai #gemma #googlecloud #llm
4
Comments
10 min read
I Tested Every Gemma 4 Model on a GTX 1650. Here's What Actually Happened.

Gemma 4 Challenge: Write about Gemma 4 Submission
sreejit_ profile

I Tested Every Gemma 4 Model on a GTX 1650. Here's What Actually Happened.

#devchallenge #gemmachallenge #gemma #ai
14
Comments 8
11 min read
I Ran an AI Model on My Phone. No Cloud. No API Keys. Just Gemma 4 and Termux.

Gemma 4 Challenge: Write about Gemma 4 Submission
okeke_chukwudubem_5f3bf49 profile

I Ran an AI Model on My Phone. No Cloud. No API Keys. Just Gemma 4 and Termux.

#devchallenge #gemmachallenge #gemma
13
Comments 2
4 min read
Gemma 4 26B on v6e-4 Turbo-Stable Benchmark

Gemma 4 Challenge: Write about Gemma 4 Submission
xbill profile

Gemma 4 26B on v6e-4 Turbo-Stable Benchmark

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