Compact variant of Meta's promptable segmentation model that returns object masks from points or boxes and can track them across video frames.
facebook/sam3
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelSegmentation860M paramsEst. 24 GB GPUEstimated minimum compute for inference: Desktop GPU with about 24 GB of memory. Not a benchmark.Custom licenseCustom or unstated terms. The upstream license governs use.GatedGated upstream: accept the owner's terms on Hugging Face to download.Single armMobile baseHumanoid
About
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.
Why it matters for physical AI
Text-prompted instance masks let a robot act on commands like 'the red mugs' without training a custom detector.
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.
Gated upstream. Accept the owner's terms on Hugging Face and sign in with hf auth login before downloading.
hf download facebook/sam3Uses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.