Instructions to use facebook/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="facebook/sam3")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Access request pending: SAM 3.1 edge deployment benchmark on Jetson Orin Nano
Hi SAM 3 team,
I’m a college student building an edge-to-cloud routing project for the Meta Global AI Developer Hackathon (deadline Nov 4). I requested access to the SAM 3 gated collection this morning (October 31st).
I am already running SAM 2.1 on the device in my pipeline (Jetson Orin Nano 8 GB), and I’d like to move to SAM 3 for its text-prompted segmentation. The model already builds and runs on the Jetson from the official repo (841M params, ~1.3 s/image after warm-up, ~4 GB peak), measured with placeholder weights. I’d like to report real-weight accuracy and latency alongside the cloud SAM 3.1 results from the Meta Model API.
If it’s possible to review my request before the deadline, I’d really appreciate it.
HF username: tejd05
Thank you for your time.