gemma4.devgemma4.dev
MkSaaS Docs
gemma4.devgemma4.dev
MkSaaS Docs
HomepageGemma 4 Developer Hub
X (Twitter)

Gemma 4 Developer Hub

Everything you need to run, deploy, and debug Gemma 4 models — from edge devices to production clusters.

Gemma 4 Developer Hub

Welcome to gemma4.dev — the independent community reference for Google's Gemma 4 model family.

What's here

Getting Started

Choose your runtime and run your first Gemma 4 model in under 5 minutes.

Model Reference

Compare E2B, E4B, 26B A4B, and 31B across context, VRAM, and use-case fit.

Concepts

Thinking mode, multimodal inputs, quantization, and prompt formatting.

Quick paths

I want to…Start here
Run locally on my laptopOllama quickstart
Deploy to productionvLLM guide
Use the smallest modelE2B specs
Enable reasoning / thinkingThinking mode
Fix a specific errorError hub

Model family at a glance

ModelParametersContextMin VRAM
Gemma 4 E2B2B (dense)8K1.4 GB
Gemma 4 E4B4B (dense)32K3.2 GB
Gemma 4 26B A4B26B (MoE, 4B active)128K16.4 GB
Gemma 4 31B31B (dense)256K24 GB

About gemma4.dev

gemma4.dev is an independent community project by Midnight Lab. It is not affiliated with Google. All guides are tested against real hardware.

Getting Started

Run your first Gemma 4 model in under 5 minutes.

Table of Contents

Gemma 4 Developer Hub
What's here
Quick paths
Model family at a glance
About gemma4.dev