---
license: gemma
base_model:
- google/gemma-4-e2b-it
pipeline_tag: image-text-to-text
tags:
- renesas
- x5h
- coming-soon
- vlm
- generative_ai
---

# Gemma4-E2B – Renesas X5H

<p align="center">
  <img src="https://ai.google.dev/gemma/images/gemma4_banner.png" alt="Gemma 4" width="720">
</p>
<p align="center"><sub>Source: <a href="https://ai.google.dev/gemma/docs/core/model_card_4">Google AI for Developers — Gemma 4 model card</a></sub></p>

🚧 **Coming soon.** This model is being optimized and validated for Renesas hardware — no fixed release date yet.

## Introduction

**Gemma4-E2B** is a small multimodal model from Google's Gemma family (the "E2B" elastic-parameter variant, ~2B effective parameters), supporting text and image input. Renesas is preparing an optimized deployment of this model for the R-Car Gen5 platform.

- **Model Architecture:** Multimodal (vision + text) small language model.
- **Source Model:** [google/gemma-4-e2b-it](https://huggingface.co/google) *(exact upstream repo to be confirmed)*

*This page is a placeholder. Content — including the source-model link — is provisional and subject to change before the model is fully published.*