Molmo2-ER
- AI model
- Perception
Ai2's open vision-language model family Molmo2 (and MolmoPoint, a pointing extension), with code to train, evaluate, and run it for image, multi-image and video understanding.
Made by Ai2, United States (checked on github.com/allenai (opens in a new tab)).
Source on GitHub: github.com/allenai/molmo2 (opens in a new tab). Facts read at commit f3cb108 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit f3cb108 (opens in a new tab), on 16 Oct 2026.
- Weights
- Apache-2.0 (opens in a new tab)
Read on huggingface.co/allenai/Molmo2-ER-4B (opens in a new tab).
- Commercial use
- Yes
What it does
- Covers video understanding, pointing, and tracking, with grounding in single-image, multi-image, and video tasks.
- Provides a three-stage training pipeline: pre-training, supervised fine-tuning, and long-context fine-tuning.
- Includes scripts to download and visualize the training and evaluation datasets.
- Offers evaluation scripts covering many image, multi-image, and video benchmarks.
- Releases checkpoints in 4B, 8B and O-7B sizes at each training stage, and supports context parallelism for long videos.
Written by Robotheca from the project's README (opens in a new tab) at commit f3cb108.
Getting started
- Difficulty
- Intermediate
- Hardware it needs, as the project states it
- Python 3.11 or later is recommended.
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 18 Mar 2026 on main
- Latest release
- None published on GitHub
Checked on GitHub on 16 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.