# Google Releases Gemma 4 Multimodal Open Model

> The new 26-billion-parameter model from DeepMind uses a mixture-of-experts design for greater efficiency and is tuned for assistant-style tasks.

Published by The Open Weights on Apr 23, 2026. Canonical: https://theopenweights.com/news/gemma-4-26b-a4b-moe-z8tk

## Key facts

- Company: Google DeepMind
- Model: Gemma 4 26B-A4B Instruct (MoE)
- Version: 4
- Category: Any-to-Any
- Modalities: Any-to-Any, Text / LLM, Vision-Language
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 26B (mixture of experts)
- Active parameters: 3.8B
- Context window: 262K tokens
- Architecture: Gemma4AssistantForCausalLM
- Precision: BF16
- Significance: notable
- Published: 2026-04-23
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/google/gemma-4-26B-A4B-it-assistant
- Canonical URL: https://theopenweights.com/news/gemma-4-26b-a4b-moe-z8tk

Google DeepMind has expanded its open-source offerings with the release of Gemma 4, a new generation of its popular model family. The initial variant, [Gemma 4 26B-A4B Instruct](https://huggingface.co/google/gemma-4-26B-A4B-it-assistant), is a powerful multimodal model designed for conversational AI and assistant tasks.

## Efficient by Design

Gemma 4 employs a sparse Mixture-of-Experts (MoE) architecture, a design choice that balances model scale with computational cost. While the model contains a total of 26 billion parameters, only 4 billion are active during inference for any given input. This approach allows Gemma 4 to achieve the performance associated with larger models while requiring significantly less processing power.

Key specifications include:
*   **Total Parameters:** 26 billion
*   **Active Parameters:** 4 billion
*   **Modalities:** Text and Vision (VLM)
*   **License:** Apache 2.0

This release is notable for its multimodal capabilities. As a vision-language model (VLM), Gemma 4 can understand and process both text and image inputs, making it suitable for a wide range of applications from image captioning to visual Q&A. This specific version is instruction-tuned, meaning it has been optimized to follow user prompts and engage in helpful dialogue.

By releasing Gemma 4 under the permissive Apache 2.0 license, Google continues to support the open-source AI community. This allows developers and researchers to freely build upon, modify, and deploy the model for both academic and commercial purposes, further accelerating innovation in the field.

## Get the model

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

## Sources

- [google/gemma-4-26B-A4B-it-assistant](https://huggingface.co/google/gemma-4-26B-A4B-it-assistant) — Hugging Face, Apr 23, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Google Releases Gemma 4 Multimodal Open Model", The Open Weights, Apr 23, 2026, https://theopenweights.com/news/gemma-4-26b-a4b-moe-z8tk