Model release

Molmo2-O 7B

Molmo2-O 7B is an open-weight model release in the Molmo family from Ai2 (Allen Institute for AI)1, version Molmo2-O-7B, released Dec 2025. Its weights can be downloaded by the public1 4 under the Apache License 2.01.

Molmo2-O-7B is the Molmo 2 vision-language model built on Ai2's Olmo 3 7B Instruct language model with a SigLIP 2 vision encoder, released in December 2025. It accepts images, multiple images, and video with text, and can answer questions, caption, and point to or track objects. Ai2 describes it as the variant whose full model flow is open, since its language model is also Ai2's.1 2

Model hub: Model card (Hugging Face) (external site: huggingface.co)
Repository: Training and inference code (allenai/molmo2) (external site: github.com)
Paper: Molmo 2 paper (arXiv 2601.10611) (external site: arxiv.org)
Release notes: Molmo 2 announcement (external site: allenai.org)

On AI on Hugging Face: allenai/Molmo2-O-7B, allenai/Molmo2-Cap

Last reviewedSep 29, 2026Entry updated Sep 29, 2026Documented release Dec 2025

Availability and license

Overall availability

Public

Downloadable from Hugging Face without gating. The card says the model is intended for research and educational use under Ai2's Responsible Use Guidelines and was trained on third-party datasets that are limited to academic and non-commercial research use.1

Availability fact review: not separately recorded

Availability is separate from permission: read the license before using or redistributing.

Apache License 2.0 (external site: huggingface.co)1
Applies to: Weights · SPDX Apache-2.0 · on the rubric’s OSI-approved software-license list · fact-level rights review not recorded
Plain-language guide to the Apache License 2.0
Apache License 2.0 (allenai/molmo2) (external site: raw.githubusercontent.com)5
Applies to: Code · SPDX Apache-2.0 · on the rubric’s OSI-approved software-license list · fact-level rights review not recorded
Plain-language guide to the Apache License 2.0

The weights are Apache 2.0, but the card states the model is intended for research and educational use in line with Ai2's Responsible Use Guidelines, and that some of its third-party training data is limited to academic and non-commercial research use, so users should review those sources. Ai2's Molmo2 datasets are ODC-BY; the Molmo2-Cap card adds that it contains text captions generated with GPT-4.1 and GPT-5, subject to OpenAI's terms.1 7 6

Component reuse rights

A readable or downloadable component is not automatically reusable. These indicators concern recorded license evidence, not system certification.

weights: Unknown — no complete fact-level rights review
code: Unknown — no complete fact-level rights review
data: Unknown — no complete fact-level rights review
documentation: Unknown — no complete fact-level rights review

No complete system-rights review is recorded for this release.

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.2. An editorial category, not a certification.

Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.2. Unknown means unassessed or insufficient evidence.

Public materials checklist for Molmo2-O 7B
Item	Status	Notes and evidence
WeightsCan the general public download the model parameters for this release?	Public	Final weights are on Hugging Face; the molmo2 repository also links pretraining and SFT checkpoints for Molmo2-O-7B.1 4
Inference codeIs code for running the model published?	Public	The card documents inference with Transformers 4.57.1 (with trust_remote_code), and the repository documents vLLM inference.1 4
Training codeIs the code used to train the model published?	Public	The card said training code would follow later; the allenai/molmo2 repository now publishes pretraining, SFT, long-context SFT, and evaluation scripts, with Molmo2-O-7B trained using the olmo3_7b_instruct setting.1 4
Training-data informationDoes the information cover provenance, scope, acquisition, selection, labeling, processing, and where data or alternatives can be obtained? Access alone does not establish completeness.	Unknown	Not assessed.
Training-data accessCan the training data be obtained? This is independent of information completeness and reuse rights; original unshareable data need not be downloadable.	Unknown	Not assessed.
Complete training pipelineIs the complete base-training and preprocessing pipeline published, including configuration? Fine-tuning code or an inference SDK alone is insufficient.	Unknown	Not assessed.
Legacy data assessment (v0.1)Historical assessment combining download access and disclosure. Preserved for traceability; excluded from the v0.2 tier calculation. See the new separate assessments above.	Partial	Ai2's nine Molmo2 datasets are public on Hugging Face (ODC-BY), and the repository provides download scripts for the academic datasets; some of those must be downloaded manually under their own licensing agreements. The Olmo 3 language model's training data is documented on its own record.1 2 4 6
Training recipeAre the training configuration and procedure documented in enough detail to follow?	Public	The Molmo 2 paper and the repository describe the pretraining, SFT, and long-context SFT stages.3 4
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.	Public	The card reports an average over 15 academic benchmarks and points to the technical report; the repository includes evaluation scripts.1 4

What it is useful for

Video and image question answering, captioning, counting, and grounding (pointing and tracking), as shown in the model card's examples.1

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.

The model card's quick start installs transformers 4.57.1 with torch, accelerate, decord2, and molmo_utils, and loads the model with trust_remote_code=True.1

Organization context

Ai2 (Allen Institute for AI)

Provenance and derivatives

Built by Ai2 from its own Olmo 3 7B Instruct language model and a SigLIP vision encoder published by Google (the card names SigLIP 2 and links google/siglip-so400m-patch14-384), then trained on Ai2's Molmo2 datasets and third-party academic datasets. The paper states the new Molmo2 data was collected without using closed vision-language models; the Molmo2-Cap card states that some of its text captions were generated with OpenAI's GPT-4.1 and GPT-5.1 3 6

Derived from: Olmo 3 7B Instruct — Language model backbone (Ai2).
Derived from: SigLIP (google/siglip-so400m-patch14-384) (external site: huggingface.co) — Vision encoder published by Google.
Derived from: Molmo2 datasets (external site: huggingface.co) — Ai2's image, multi-image, and video training data (ODC-BY).

Other releases in the Molmo family

No other releases in this family have been assessed.

Molmo family overview

What this catalog does not know

Unknown means the sources reviewed for this record do not document it. It is not evidence that something does not exist.

Training-data information: unknown.
Training-data access: unknown.
Complete training pipeline: unknown.

Have a primary source? How to report a correction.

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. nonprofit or lab

The model card states the Molmo2 family was developed by the Allen Institute for AI (Ai2), which describes itself as a Seattle-based non-profit AI research institute. Its language model, Olmo 3 7B Instruct, is also an Ai2 model.1 8

Assessed Sep 29, 2026

Sources

1.
allenai/Molmo2-O-7B model card (external site: huggingface.co)
Ai2 · Model card · accessed Sep 29, 2026
2.
Molmo 2: State-of-the-art video understanding, pointing, and tracking (external site: allenai.org)
Ai2 · Announcement · published Dec 2025 · accessed Sep 29, 2026
3.
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding (arXiv 2601.10611) (external site: arxiv.org)
Ai2 (arXiv) · Paper · published Jan 15, 2026 · accessed Sep 29, 2026
4.
allenai/molmo2 README (external site: raw.githubusercontent.com)
Ai2 · Repository · accessed Sep 29, 2026
5.
allenai/molmo2 LICENSE (external site: raw.githubusercontent.com)
Ai2 · License · accessed Sep 29, 2026
6.
allenai/Molmo2-Cap dataset card (external site: huggingface.co)
Ai2 · Dataset card · accessed Sep 29, 2026
7.
Responsible use guidelines | Ai2 (external site: allenai.org)
Ai2 · Official page · accessed Sep 29, 2026
8.
About us | Ai2 (external site: allenai.org)
Ai2 · Official page · accessed Sep 29, 2026

Email a correction Report a correction Edit this entry

This listing is not an endorsement, a safety assessment, or a federal approval.

Cite this page

APA style

USASI. (2026, September 29). Molmo2-O 7B. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/open/molmo2-o-7b/

BibTeX

@misc{usasi_molmo2_o_7b,
  author = {{USASI}},
  title = {Molmo2-O 7B},
  year = {2026},
  month = sep,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/open/molmo2-o-7b/}},
  note = {United States of America Superintelligence. Last updated 2026-09-29}
}

The date is when this page was last updated. Add the date you read it if your style needs one.

For maintainers: a “Listed in USASI” badge

Links to this page. It says the entry is listed, not endorsed or rated. About the badge

Markdown (for a README)

[![Listed in the USASI catalog](https://unitedstatesofamericasuperintelligence.com/badges/listed.svg)](https://unitedstatesofamericasuperintelligence.com/open/molmo2-o-7b/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/open/molmo2-o-7b/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/listed.svg" alt="Listed in the USASI catalog" height="20"></a>