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

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Your SOS app can’t Help if you can’t reach your phone — so I want to built a local AI Safety Layer with gemma 4

Gemma 4 Challenge: Write about Gemma 4 Submission

Your SOS app can’t Help if you can’t reach your phone — so I want to built a local AI Safety Layer with gemma 4

12
Comments 2
6 min read
Gemma 4 and the Architecture of On-Device AI

Gemma 4 and the Architecture of On-Device AI

Comments
3 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
Same model. Different results. — AgentKit Benchmark + OpenCode Integration

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

Comments
2 min read
Gemma 4: Byte for byte, the most capable open models

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

8
Comments
15 min read
I Ran Google's New Gemma 4 Models Locally (26B and 31B) — Here's What I Found

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

Comments
4 min read
Cut AI Costs: Flutter On-Device LLM Integration Works

Cut AI Costs: Flutter On-Device LLM Integration Works

Comments
10 min read
Fine-Tuning Gemma 4 with Cloud Run Jobs: Serverless GPUs (NVIDIA RTX 6000 Pro) for pet breed classification 🐈🐕

LoRA workarounds for custom model layers

Fine-Tuning Gemma 4 with Cloud Run Jobs: Serverless GPUs (NVIDIA RTX 6000 Pro) for pet breed classification 🐈🐕

67
Comments 9
9 min read
We Gave an AI Agent a Long Context Caching Idea. Here's what happened next!

We Gave an AI Agent a Long Context Caching Idea. Here's what happened next!

2
Comments
7 min read
Mastering Gemma 4: A Comprehensive Deep Dive into Google's Next-Generation Open Model Architecture and Deployment

Mastering Gemma 4: A Comprehensive Deep Dive into Google's Next-Generation Open Model Architecture and Deployment

2
Comments
7 min read
Building a Systemic Autonomy Agent: OpenClaw + Gemma 4 & TurboQuant on Raspberry Pi 4B

OpenClaw Challenge Submission 🦞

Building a Systemic Autonomy Agent: OpenClaw + Gemma 4 & TurboQuant on Raspberry Pi 4B

17
Comments 5
11 min read
Reverse Engineering SynthID: What Happens to Gemini's Watermark When the Model Runs in Your Browser?

Reverse Engineering SynthID: What Happens to Gemini's Watermark When the Model Runs in Your Browser?

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

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

31
Comments 2
14 min read
Building a Multimodal Local AI Stack: Gemma 4 E2B, vLLM, and Hermes Agent

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

1
Comments
2 min read
Gemma 3 on a Raspberry Pi 5: I Benchmarked Google's Open Model on a $80 Computer [2026]

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

Comments 2
7 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.