# Gemma 4 — open models for reasoning and agents

> Four open models from Google under Apache 2.0 that bring frontier-tier reasoning and native tool-use to consumer GPUs and phones.

- Org: Google DeepMind
- Date: 2026-04-02
- Category: model, repo
- Source: https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
- Canonical page: https://ai-tldr.dev/releases/google-gemma-4/

## In short

Google DeepMind ships four Gemma 4 sizes (E2B, E4B, 26B MoE, 31B dense) under Apache 2.0 with 256K context, native vision/audio, and agentic tool-use built in. The 31B scores 89.2% on AIME 2026.

## What it is

Gemma 4 is Google DeepMind's latest family of open-weights models, built from the same research as Gemini 3 and released on April 2, 2026. It ships in four sizes: E2B (2.3B effective) and E4B (4.5B effective) for edge and mobile, a 26B Mixture-of-Experts (4B activated) for mid-range hardware, and a 31B dense model for workstations. Every variant ships under Apache 2.0 with no usage caps.

## How it works

All four models are natively multimodal (text, image, video; audio on the small models) with context windows up to 256K tokens. The 31B instruction-tuned model scores 89.2% on AIME 2026 (up from 20.8% on Gemma 3 27B), 84.3% on GPQA Diamond, and 86.4% on the tau2-bench agentic tool-use benchmark. Native function calling is built in, so the models can drive tools and APIs without prompt hacking.

## Why it matters

This is the first Apache 2.0 model family that competes with frontier proprietary models on both reasoning and agentic benchmarks while still fitting on a phone (E2B) or a single GPU (31B). The license means anyone can deploy, modify, and redistribute without restrictions or revenue caps.

## Who it's for

On-device ML engineers, self-hosters, agent framework authors, Android developers.

## Try it

huggingface.co/google/gemma-4-31B-it

## Links

- [Announcement](https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/)
- [HF blog](https://huggingface.co/blog/gemma4)
- [Model card (31B)](https://huggingface.co/google/gemma-4-31B-it)
- [DeepMind page](https://deepmind.google/models/gemma/gemma-4/)