DataLearner logo
ER

ERNIE-4.5-VL-28B-A3B

Retired · 2026-06-09Multimodal modelERNIE-4.5

ERNIE-4.5-VL-28B-A3B Multimodal MoE Chat Model

Release date: 2025-08-20Updated: 2026-09-04Retired: 2026-06-09Views: 179
Parameters
28B
Context length
131K
Multilingual
Supported
Reasoning ability
3/5

ERNIE-4.5-VL-28B-A3B Multimodal MoE Chat Model is an AI model published by Baidu, released on 2025-08-20, for Multimodal model, with 28B parameters, and 131K context length.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

ERNIE-4.5-VL-28B-A3B

Model basics

Reasoning traces
Supported
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
131K tokens
Max output length
No data
Model type
Multimodal model
Modality (in / out)
Text, Image, Video → Text, Image, Video
Release date
2025-08-20
Model file size
No data
MoE architecture
Yes
Total params / Active params
28B / 3B
Knowledge cutoff
No data
ERNIE-4.5-VL-28B-A3B

Open source & experience

Code license
Weights license
Apache 2.0- Commercial use permitted
Live demo
N/A
ERNIE-4.5-VL-28B-A3B

Official resources

Paper
DataLearnerAI blog
N/A
ERNIE-4.5-VL-28B-A3B

API details

API speed
3/5
No public API pricing yet.
ERNIE-4.5-VL-28B-A3B

Publisher

ERNIE-4.5-VL-28B-A3B Multimodal MoE Chat Model

Model Overview

ERNIE-4.5-VL-28B-A3B Multimodal MoE Chat Model is an AI model published by Baidu, released on 2025-08-20, for Multimodal model, with 28B parameters, and 131K context length.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code