Molmo2-O

About

What Molmo2-O is

Molmo2 Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding. Molmo2 models are trained on publicly available third party datasets as referenced in our technical report and Molmo2 data, a collection of datasets with highly-curated image-text and video-text pairs. It has state-of-the-art performance among multimodal models with a similar size. You can find all models in the Molmo2 family here. Learn more about the Molmo2 family in our announcement blog post. Molmo2-O-7B is based on Olmo3-7B-Instruct and uses SigLIP 2 as vision backbone. It outperforms others in the class of open weight and data models on short videos, counting, and captioning, and is competitive on long-videos. Ai2 is commited to open science. The Molmo2 datasets are available here. All other artifacts used in creating Molmo2 (training code, evaluations, intermediate checkpoints) will be made available at a later date, furthering our commitment to open-source AI development and reproducibility. Quick links: - 📂 All Models - 📃 Paper - 🎥 Blog with Videos Quick Start Setup Conda Environment General Video QA Pointing Video QA Tracking Video QA Multi-image QA Multi-Image Point QA Evaluations We report the Average Score on 15 Academic Benchmarks here. For details on the evals, refer to the main video results table in our technical report. License and Use This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2’s Responsible Use Guidelines. This model is trained on third party datasets that are subject to academic and non-commercial research use only. Please review the sources to determine if this model is appropriate for your use case.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys molmo2-o for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (molmo2-o below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"molmo2-o","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models