Molmo2-VideoPoint-4B

allenai/Molmo2-VideoPoint-4B

Video Text To Text4.9B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 5, 2026View on Hugging Face ↗
Downloads 30D
199
Total downloads
47.3K
Gained 7D
0
0% vs baseline
Gained 30D
—
Likes
22
+0 in 7D
Rank · tracked models
#51,743
401(down 401 places)this week
Parameters
4.9B
Last source update
Dec 16, 2025
Momentum
4.4

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

Molmo2-VideoPoint-4B is a video text to text model published by allenai. OpenModelStats has tracked the model since Sep 5, 2026, most recently observing it Sep 4, 2026.

Published
Dec 16, 2025
Last updated
Dec 16, 2025
Library
transformers
License
apache-2.0
Task
Video Text To Text
Parameters
4,850,869,200
Spaces
—
Derivative models
—
Velocity 7D/day
0
transformerssafetensorsmolmo2image-text-to-textmultimodalolmomolmovideo-text-to-textcustom_codeendataset:allenai/Molmo2-VideoPointdataset:allenai/pixmo-points

Publisher

allenaiView publisher statistics →

Derived from Qwen/Qwen3-4B-Instruct-2507 (reported by the source; parent not yet tracked).

Similar models

Models similar to Molmo2-VideoPoint-4B
ModelDL 30D
Code-as-World-VL-4BMirroS-Lab489
VideoChat3-4BMCG-NJU2,552
TimeLens2-4BMCG-NJU1,344
CASA-Qwen2_5-VL-3B-LiveCCkyutai2,429
UGC-VideoCaptioneropeninterx1,405
GenS-qwen2d5-vl-3byaolily4,783
allenai/Molmo2-VideoPoint-4B — Downloads, Growth & Stats | OpenModelStats