Released April 2, 2026

Gemma 4 Byte for byte, the most capable open models

Purpose-built for advanced reasoning and agentic workflows. Google DeepMind's breakthrough open model family — Apache 2.0 licensed, frontier performance, runs on your hardware.

400M+
Downloads since Gemma 1
100K+
Community variants
#3
Open model on Arena AI
Core Capabilities

Built for modern AI workflows

Six breakthrough capabilities in a single, open-source model family.

🧠

Advanced Reasoning

Multi-step planning and deep logic. Major improvements in math (AIME 2026: 89.2%) and instruction-following benchmarks, enabling complex problem decomposition.

🤖

Agentic Workflows

Native function calling, structured JSON output, and system instructions. Build autonomous agents that interact with tools and APIs to execute complex workflows reliably.

💻

Code Generation

High-quality offline code generation. Turn your workstation into a local-first AI code assistant. Scores 80% on LiveCodeBench v6 competitive coding problems.

👁️

Multimodal — Vision, Video & Audio

All models natively process images and video at variable resolutions, excelling at OCR and chart understanding. E2B/E4B also support native audio input for speech recognition.

🌍

140+ Languages

Natively trained on over 140 languages. Build inclusive, high-performance applications for a global audience with state-of-the-art multilingual understanding (MMMLU: 85.2%).

📄

Ultra-Long Context

Process long-form content seamlessly. Edge models support a 128K context window; larger models extend to 256K tokens — pass entire repositories or long documents in one prompt.

Benchmarks

Outperforms models 20× its size

Gemma 4 31B ranks #3 among all open models on Arena AI's text leaderboard. The 26B MoE holds #6 — achieving frontier-level intelligence at a fraction of the compute cost.

85.2%
MMMLU (multilingual)
89.2%
AIME 2026 (math)
80.0%
LiveCodeBench v6
1452
Arena AI Score
See full benchmarks →
Benchmark comparison (31B vs previous gen)
MMMLU
Prev: 67.6% G4: 85.2%
AIME 2026
Prev: 20.8% G4: 89.2%
LiveCodeBench v6
Prev: 29.1% G4: 80%
GPQA Diamond
Prev: 42.4% G4: 84.3%
🚀

Ready to build with Gemma 4?

Apache 2.0 licensed. Available on Hugging Face, Ollama, Kaggle, LM Studio, and more. Start in minutes.

View Quick Start Guide →