Note that this is the molmo-native checkpoint, and it's NOT Huggingface/transformers-compatible. Check out
allenai/MolmoWeb-8B for HF-compatible checkpoint.
MolmoWeb is a family of fully open multimodal web agents. MolmoWeb agents achieve state-of-the-art results outperforming similar scale open-weight-only
models such as Fara-7B, UI-Tars-1.5-7B, and Holo1-7B. MolmoWeb-8B also surpasses set-of-marks
(SoM) agents built on much larger closed frontier models like GPT-4o. We further demonstrate
consistent gains through test-time scaling via parallel rollouts with best-of-N selection, achieving 94.7%
and 60.5% pass@4 (compared to 78.2% and 35.3% pass@1)on WebVoyager and Online-Mind2Web
respectively.
Learn more about the MolmoWeb family in our announcement
blog post and
tech report.
MolmoWeb-8B-Native is based on
Molmo2 architecture, which uses
Qwen3-8B and
SigLIP 2 as vision backbone.
Ai2 is committed to open science. The MolmoWeb datasets are available
here.
All other artifacts used in creating MolmoWeb (training code,
evaluations, intermediate checkpoints) will be made available, furthering our commitment to open-source AI development and reproducibility.
This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2’s
Responsible Use Guidelines.
1@misc{gupta2026molmowebopenvisualweb,
2 title={MolmoWeb: Open Visual Web Agent and Open Data for the Open Web},
3 author={Tanmay Gupta and Piper Wolters and Zixian Ma and Peter Sushko and Rock Yuren Pang and Diego Llanes and Yue Yang and Taira Anderson and Boyuan Zheng and Zhongzheng Ren and Harsh Trivedi and Taylor Blanton and Caleb Ouellette and Winson Han and Ali Farhadi and Ranjay Krishna},
4 year={2026},
5 eprint={2604.08516},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2604.08516},
9}
