# Google DeepMind's Gemma 4 Goes Multimodal and MoE

> The new open-weights family adds a mixture-of-experts design, encoder-free multimodal inputs, and an optional thinking mode.

Published by The Open Weights on Jul 1, 2026. Canonical: https://theopenweights.com/news/gemma-4-l0lj

## Key facts

- Company: Google DeepMind
- Model: Gemma 4
- Version: 4
- Category: Any-to-Any
- Modalities: Any-to-Any, Text / LLM, Vision-Language, Reasoning
- License: Gemma (Open weights, commercial use allowed)
- Significance: major
- Published: 2026-07-01
- Last verified: 2026-07-09
- Canonical URL: https://theopenweights.com/news/gemma-4-l0lj

Google DeepMind has introduced Gemma 4, the latest generation of its open-weights model family, according to the [Gemma 4 Technical Report](https://huggingface.co/papers/2607.02770). The release marks a notable architectural shift, moving the family toward a mixture-of-experts (MoE) design while broadening its native support for text, images, and reasoning-heavy tasks.

The headline changes are structural. Gemma 4 adopts an MoE approach, which activates only a subset of parameters per token to improve efficiency relative to dense models of comparable capacity. The family is also described as encoder-free for multimodal inputs, suggesting a more unified path for handling images and text without a separate vision encoder stage.

## What's new in Gemma 4

- A mixture-of-experts architecture across the family
- Encoder-free multimodal handling for text and vision
- An optional thinking mode for step-by-step reasoning
- Support for long context

The thinking mode places Gemma 4 alongside a growing set of models that expose explicit reasoning behavior, letting developers trade extra compute for stronger performance on complex problems. Combined with long-context support, that positions the family for tasks that span large documents or multi-step workflows.

Gemma 4 continues to ship under the Gemma license, keeping the weights accessible for developers and researchers who want to build on or fine-tune the models directly. Why it matters: an open MoE multimodal family with reasoning controls narrows the gap between open weights and the capabilities typically reserved for closed frontier systems, giving teams more room to self-host and customize.

## Get the model

- [HF Papers](https://huggingface.co/papers/2607.02770)

## Sources

- [Gemma 4 Technical Report](https://huggingface.co/papers/2607.02770) — HF Papers, Jul 1, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Google DeepMind's Gemma 4 Goes Multimodal and MoE", The Open Weights, Jul 1, 2026, https://theopenweights.com/news/gemma-4-l0lj