# Google's Gemma 4 Arrives with Any-to-Any Multimodal Skills

> The new 2-billion-parameter model from DeepMind can process text, vision, and audio, making it a versatile and efficient foundation for developers.

Published by The Open Weights on Mar 2, 2026. Canonical: https://theopenweights.com/news/gemma-4-e2b-a40j

## Key facts

- Company: Google DeepMind
- Model: Gemma 4 E2B
- Version: 4
- Category: Any-to-Any
- Modalities: Any-to-Any, Vision-Language, Text / LLM
- License: Gemma (Open weights, commercial use allowed)
- Parameters: 2B
- Context window: 131K tokens
- Architecture: Gemma4ForConditionalGeneration
- Precision: BF16
- Significance: major
- Published: 2026-03-02
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/google/gemma-4-E2B-it
- Canonical URL: https://theopenweights.com/news/gemma-4-e2b-a40j

Google DeepMind has released Gemma 4 E2B IT, the first model in a new generation of its open-weights AI family. This compact, 2-billion-parameter model is distinguished by its native "any-to-any" multimodality, capable of processing and generating combinations of text, vision, and audio.

The "E2B" in the name likely stands for "Efficient 2 Billion," highlighting the model's focus on performance within a small footprint. As an instruction-tuned (`-it`) variant, it's optimized for chat and direct-response tasks and features a context window of 8192 tokens.

## Why It Matters

Gemma 4's release marks a significant step for developers seeking powerful AI that can run efficiently on local hardware or in resource-constrained cloud environments. By integrating text, vision, and audio capabilities into a single, compact model, Google is making sophisticated, multi-sensory AI more accessible and lowering the barrier for building complex applications.

The model is available now for researchers and developers on [Hugging Face](https://huggingface.co/google/gemma-4-E2B-it). It is released under the Gemma license terms, which permit commercial use but include specific restrictions, continuing Google's strategy of providing capable but controlled open-source tools.

## Get the model

- [Hugging Face](https://huggingface.co/google/gemma-4-E2B-it)

## Sources

- [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) — Hugging Face, Mar 2, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Google's Gemma 4 Arrives with Any-to-Any Multimodal Skills", The Open Weights, Mar 2, 2026, https://theopenweights.com/news/gemma-4-e2b-a40j