ERNIE-4.5-VL-28B-A3B-Thinking: A Breakthrough in Multimodal AI

• multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
• reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
• mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.

ERNIE-4.5-VL-28B-A3B-Thinking activates only 3B parameters yet claims state-of-the-art multimodal reasoning results, an efficiency data point for teams evaluating sparse-MoE VLMs.

• articleERNIE 5.0: A 2.4 Trillion-Parameter Unified Multimodal Foundation Modelunknown
• articleERNIE 5.1 Officially Released! Topping Multiple Leaderboards — A Model That Writes Better and Understands You Moreunknown
• articleAnnouncing the Open Source Release of the ERNIE 4.5 Model Familyunknown

Checking sign-in…

Loading comments…