Tendem
Mini toolsMolmo 2
By Ai2
New
Text
Gen 4
Overview
Molmo 2 is AI2’s open 4B/7B/8B multimodal model for images and video, delivering state-of-the-art grounded video QA, pointing and tracking that return coordinates and timestamps for events instead of text-only answers.
Description
Molmo 2 is Allen AI’s next generation Molmo family, extending image pointing to video and multi-image understanding. It comes in 4B and 8B Qwen 3 based variants plus a 7B Olmo-backed Molmo 2-O. The model grounds answers in space and time, supporting video QA, counting, dense captioning and multi-object tracking that outputs points, IDs and timestamps, and achieves leading open-weight results on many multimodal benchmarks.
About Ai2
We are a Seattle based non-profit AI research institute founded in 2014 by the late Paul Allen. We develop foundational AI research and innovation to deliver real-world impact through large-scale open models, data, robotics, conservation, and beyond.
Website:
allenai.org
Last updated: December 17, 2025
