# muse-glimmer-30b-torch Agentic 30B vision-language model for object detection via 2D grounding. **Details** - Model name: `muse-glimmer-30b-torch` - Model source: [https://huggingface.co/meta-models/Muse-Glimmer-30B](https://huggingface.co/meta-models/Muse-Glimmer-30B) - Model author: Meta - Model license: Apache 2.0 - Model size: 55.51 GB - Exposes embeddings? no - Tags: `detection, vlm, torch, transformer, zero-shot` **Requirements** - Packages: `torch, torchvision, transformers>=5.15.0, accelerate` - CPU support - yes - GPU support - yes **Example usage** ```python import fiftyone as fo import fiftyone.zoo as foz 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("muse-glimmer-30b-torch") dataset.apply_model(model, label_field="predictions") session = fo.launch_app(dataset) ```