# allenai/MolmoPoint-8B From Plugin #### NOTE This is a [remotely-sourced model](../remote.md#model-zoo-remote) from the [molmo_point](../../plugins/plugins_ecosystem/molmo_point.html) plugin, maintained by the community. It is not part of FiftyOne core and may have special installation requirements. Please review the plugin documentation and license before use. MolmoPoint-8B is a vision-language model that locates and tracks objects in images and videos by pointing. For images, it returns normalized keypoint coordinates per instance. For videos, it supports frame-level tracking (follows objects over time) and sparse pointing (identifies objects across sampled frames).. **Details** - Model name: `allenai/MolmoPoint-8B` - Model source: [https://huggingface.co/allenai/MolmoPoint-8B](https://huggingface.co/allenai/MolmoPoint-8B) - Model author: Allen AI - Model license: Apache-2.0 - Exposes embeddings? no - Tags: `keypoints, pointing, tracking, video, VLM, zero-shot, image-text-to-text` **Requirements** - Packages: `torch, transformers, pillow, huggingface-hub, molmo-utils` - CPU support - yes - GPU support - yes **Example usage** ```python import fiftyone as fo import fiftyone.zoo as foz foz.register_zoo_model_source("https://github.com/harpreetsahota204/molmo_point") dataset = foz.load_zoo_dataset( "coco-2017", split="validation", dataset_name=fo.get_default_dataset_name(), max_samples=50, shuffle=True, ) model = foz.load_zoo_model("allenai/MolmoPoint-8B") dataset.apply_model(model, label_field="predictions") session = fo.launch_app(dataset) ```