# Baidu Releases Open Vision-Language MoE Model

> The new ERNIE 4.5 VL model brings advanced multimodal reasoning to the open-source community with an efficient Mixture-of-Experts architecture.

Published by The Open Weights on Nov 7, 2025. Canonical: https://theopenweights.com/news/ernie-4-5-vl-28b-a3b-thinking-86bx

## Key facts

- Company: Baidu
- Model: ERNIE 4.5 VL 28B A3B Thinking
- Version: 4.5-VL-Thinking
- Category: Vision-Language
- Modalities: Reasoning, Vision-Language
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 28B (mixture of experts)
- Active parameters: 3B
- Context window: 131K tokens
- Architecture: Ernie4_5_VLMoeForConditionalGeneration
- Precision: BF16
- Weights size: 59.3 GB
- Languages: English, Chinese
- Significance: notable
- Published: 2025-11-07
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-Thinking
- Canonical URL: https://theopenweights.com/news/ernie-4-5-vl-28b-a3b-thinking-86bx

Chinese tech giant Baidu has released ERNIE 4.5 VL, a powerful new vision-language model available under a permissive open-source license. The model is designed for complex reasoning tasks that require understanding both images and text, positioning it as a capable new entry in the open multimodal space.

## Efficient by Design

At its core, ERNIE 4.5 VL is a sparse Mixture-of-Experts (MoE) model. While it contains a total of 28 billion parameters, it only activates a fraction—around 3 billion—for any given inference task. This design, hinted at by the 'A3B' (Active 3 Billion) in its name, aims to provide the power of a much larger model while maintaining greater computational efficiency during use.

The model's full name, [ERNIE 4.5 VL 28B A3B Thinking](https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-Thinking), emphasizes its focus on multi-step reasoning. It's built to analyze visual information and perform logical thinking, a challenging frontier for AI development.

By releasing this model under the Apache 2.0 license, Baidu is making a notable contribution to the open-source ecosystem. This gives researchers and developers a sophisticated, efficient, and freely usable foundation for building the next generation of multimodal applications.

## Get the model

- [Hugging Face](https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-Thinking)

## Sources

- [baidu/ERNIE-4.5-VL-28B-A3B-Thinking](https://huggingface.co/baidu/ERNIE-4.5-VL-28B-A3B-Thinking) — Hugging Face, Nov 7, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Baidu Releases Open Vision-Language MoE Model", The Open Weights, Nov 7, 2025, https://theopenweights.com/news/ernie-4-5-vl-28b-a3b-thinking-86bx