ERNIE-4.5-VL-28B-A3B-PT is a large-scale multimodal model from Baidu featuring a 28B language model paired with a 3B vision component. It supports text, image, and video inputs and uses a specialized chat template for multimodal conversations. The model is part of the ERNIE family and is available on Hugging Face for research and development purposes.
ERNIE 4.5 VL 28B A3B PT sits in PulseGate's Multimodal & vision category. It focuses on understanding and reasoning over combined text, image, and video inputs in a single model. It is built as an open-source project for developers. The project is open source (Apache-2.0). ERNIE 4.5 VL 28B A3B PT is available on the web, the command line, and API.
Behind ERNIE 4.5 VL 28B A3B PT is Baidu, based in China, and it first shipped in 2025. Development happens publicly on GitHub with 7.7k stars. Key capabilities include vision-Language, Multimodal Understanding, and Video Processing.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do