Meta's third-generation segmentation model that can find, mask and track every instance of a concept described by a short text phrase or example image.
facebook/sam2.1-hiera-small
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelSegmentation46M paramsEst. Edge GPUEstimated minimum compute for inference: Jetson Orin class, 8–16 GB shared memory. Not a benchmark.Apache 2.0Single armMobile baseHumanoid
About
Compact variant of Meta's promptable segmentation model that returns object masks from points or boxes and can track them across video frames.
Why it matters for physical AI
Gives a robot pixel-accurate object masks for grasp planning and tracking at a size that fits edge GPUs.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
hf download facebook/sam2.1-hiera-smallUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
Open-vocabulary perception on a Jetson Orin: what's your pipeline?
Grounding DINO for boxes followed by SAM 2.1 for masks is a common language-driven pick-and-place front end.