Skip to content

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.

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Kunal

Apr 12

Gemma 3 on a Raspberry Pi 5: I Benchmarked Google's Open Model on a $80 Computer [2026]

#gemma #raspberrypi #localllm #googleai

7 min read

Vladimir Desyatov

Apr 12

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

#ai #gemma #ollama #robotics

4 min read

Apr 12

Gemma 4: Byte for byte, the most capable open models

#gemma #ai #open #models

15 min read

Apr 10

Reverse engineering SynthID: ¿qué pasa con el watermark de Gemini cuando el modelo corre en tu browser?

#webgpu #gemma #synthid #watermarkia

9 min read

AJAY SABLE

Apr 9

Same model. Different results. — AgentKit Benchmark + OpenCode Integration

#opensource #ai #gemma #devtools

2 min read

Amit Raz

Apr 6

I Ran Google's New Gemma 4 Models Locally (26B and 31B) — Here's What I Found

#ai #llm #gemma

4 min read

Apr 6

Cut AI Costs: Flutter On-Device LLM Integration Works

#flutter #ondeviceai #llm #gemma

10 min read

Gaurav Vij

Apr 4

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

#gemma #ai #llm #gemini

6 min read

Max Quimby

Apr 4

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

#gemma #aiagents #opensource #google

3 min read

Shir Meir Lador for Google AI

Apr 9

Fine-Tuning Gemma 3 with Cloud Run Jobs: Serverless GPUs (NVIDIA RTX 6000 Pro) for pet breed classification 🐈🐕

#nvidia #ai #gemma #serverless

14 min read

Maninderpreet Singh

Apr 5

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

#gemma #ai #programming #webdev

9 min read

akartit

Apr 4

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

#ai #machinelearning #gemma #opensource

4 min read

Karl Weinmeister for Google AI

Apr 9

On-Device AI with the Google AI Edge Gallery and Gemma 4

#aiondevice #android #ios #gemma

6 min read

Abdul Hakkeem P A

Apr 4

Building a Multimodal Local AI Stack: Gemma 4 E2B, vLLM, and Hermes Agent

#ai #gemma #hermes #mcp

2 min read

Daniel Gwerzman for Google Developer Experts

Apr 4

Deploy Gemma 4 on Cloud Run: Pay Only When You Actually Use It

#gemma #cloudrun #cloud #ai

18 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.