Model reference · open weights
MolmoMotion-H1-F32 is an open-weight language model from allenai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
MolmoMotion-4B-H1-F32 MolmoMotion is a 4B vision-language model that forecasts 3D point trajectories under natural-language action instructions. Given a short RGB observation history, a set of user-specified 2D query points with their 3D history, and an action description, it predicts where those points move in 3D (camera frame, in meters) over a future horizon. This checkpoint is the autoregressive (AR) variant with history H=1 and future horizon F=32. Pick this variant when only a single query keyframe is available. Quick Links - 📂 Models: MolmoMotion collection - 📂 Dataset: allenai/molmo-motion-1m - 📊 Benchmark: allenai/PointMotionBench - 💻 Code: allenai/molmo-motion - 🎥 Blog Post: MolmoMotion - 📄 Paper: coming soon Intended Use MolmoMotion forecasts 3D point trajectories from RGB video, 2D query points, and a language action. Use it for trajectory-prediction / motion-forecasting research and as a starting point for downstream finetuning (e.g. the robot pick-and-place recipe in robotics/). Pick the variant that matches your input: Usage Install the package, then load this checkpoint: See examples/01quickstart.py for a full forward pass (building inputs, predicttrajectory, and visualizing the predicted trajectory). Responsible Use MolmoMotion is a research model that predicts point trajectories; it is intended for research and educational use in accordance with Ai2's Responsible Use Guidelines. Predicted trajectories are model estimates and should be validated before being used to drive any downstream actuated system. Disclaimer MolmoMotion is trained on MolmoMotion-1M, which includes captions and trajectory annotations based on coordinates of objects in videos. The videos are provided by the owners of the datasets listed in allenai/molmo-motion-1m and allenai/PointMotionBench, and are subject to their respective license terms and use restrictions. Users who access videos from these sources to reconstruct any portion of the training data are responsible for reviewing and confirming that their intended use complies with the terms and conditions. Acknowledgement We thank Ropedia for providing videos from the Xperience dataset that were used in our research and d
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | allenai |
|---|---|
| Type | Language models |
| Parameters (lead) | 4.9B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-06-15 |
| Popularity | 228 downloads / month |
| Likes | 5 |
| Licence | Open weights |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| MolmoMotion-4B-H1-F32 | 4.9B | BF16 | ~11.2 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys molmomotion-h1-f32 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (molmomotion-h1-f32 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":"molmomotion-h1-f32","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗