# Google Releases Gemma 4, a 26B Vision-Language Model

> The new open-source model from DeepMind uses a Mixture-of-Experts architecture to handle both text and image inputs efficiently.

Published by The Open Weights on Mar 11, 2026. Canonical: https://theopenweights.com/news/gemma-4-26b-a4b-rzlm

## Key facts

- Company: Google DeepMind
- Model: Gemma 4
- Version: 4
- Category: Any-to-Any
- Modalities: Text / LLM, Vision-Language
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 26B (mixture of experts)
- Context window: 262K tokens
- Architecture: Gemma4ForConditionalGeneration
- Precision: BF16
- Weights size: 51.6 GB
- Languages: 140+ languages
- Significance: major
- Published: 2026-03-11
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/google/gemma-4-26B-A4B-it
- Canonical URL: https://theopenweights.com/news/gemma-4-26b-a4b-rzlm

Google DeepMind has expanded its open-source offerings with the release of Gemma 4 26B Instruct, a new vision-language model. Published under a permissive Apache 2.0 license, this model is designed to understand and process both text and images, making it a versatile tool for multimodal applications.

## An Efficient Multimodal Architecture

The key innovation in Gemma 4 is its Mixture-of-Experts (MoE) architecture. While the model contains a total of 26 billion parameters, it's designed for efficiency by activating only a fraction of them for any given task. The model's designation, "A4B," suggests that approximately 4 billion parameters are active at a time, offering potent performance without the full computational cost of a dense 26B model.

As an instruction-tuned model, Gemma 4 26B is optimized to follow user prompts and commands, making it suitable for a wide range of chat and assistant-style applications. Researchers and developers can access the model and its technical details on its [Hugging Face repository](https://huggingface.co/google/gemma-4-26B-A4B-it).

This release signals Google's continued investment in the open-source AI ecosystem, providing a powerful, state-of-the-art multimodal model to the community. The efficient MoE design makes advanced vision-language capabilities more accessible, enabling new possibilities for applications that can see and reason about the world.

## Get the model

- [Hugging Face](https://huggingface.co/google/gemma-4-26B-A4B-it)

## Sources

- [google/gemma-4-26B-A4B-it](https://huggingface.co/google/gemma-4-26B-A4B-it) — Hugging Face, Mar 11, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Google Releases Gemma 4, a 26B Vision-Language Model", The Open Weights, Mar 11, 2026, https://theopenweights.com/news/gemma-4-26b-a4b-rzlm