USASI
Model release

SAM 2.1 Hiera-Large

Release in the Segment Anything (SAM) family · version 2.1 (sam2.1_hiera_large)

Maintained by Meta (FAIR)1

SAM 2.1 Hiera-Large is the largest checkpoint (224.4M parameters, per the README) in Meta's SAM 2.1 suite, an improved set of SAM 2 checkpoints released in September 2024. SAM 2 is a transformer with streaming memory that segments objects in images and tracks them through video from point, box, or mask prompts.12

Last reviewedEntry updated Documented release Sep 29, 2024

Availability and license

Overall availability

Public

The checkpoint downloads directly from Meta's servers or from Hugging Face without gating.110

Availability is separate from permission: read the license before using or redistributing.

The README states that the SAM 2 model checkpoints, demo code, and training code are licensed under Apache 2.0. The fonts bundled with the web demo are under the SIL Open Font License 1.1, and an optional connected-components post-processing module adapted from cc_torch carries its own BSD 3-Clause license.14

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.1. An editorial category, not a certification.
Model-disclosure tier (USASI rubric v0.1): Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.1. Unknown means unassessed or insufficient evidence.
Public materials checklist for SAM 2.1 Hiera-Large
ItemStatusNotes and evidence
WeightsCan the general public download the model parameters for this release?PublicDirect download links in the README and an ungated Hugging Face repository.110
Inference codeIs code for running the model published?PublicThe repository provides image and video predictors and notebooks; the Hugging Face card also documents use with Transformers.19
Training codeIs the code used to train the model published?PublicTraining and fine-tuning code was released with SAM 2.1, including the trainer, loss functions, dataset loaders, and launch scripts for single- and multi-node jobs.25
Training-data informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access.PartialThe paper lists the training mix as SA-1B, the SA-V dataset, an internal video dataset, and open-source video datasets. SA-V is downloadable under CC BY 4.0, but the internal data is not released.86
Training recipeAre the training configuration and procedure documented in enough detail to follow?PartialThe paper's appendix tabulates pre-training and full-training hyperparameters, and the paper states its results use SAM 2.1, but it gives few details of what changed from the July 2024 checkpoints.8
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.PublicThe README reports SA-V test, MOSE val, and LVOS v2 results for each SAM 2.1 checkpoint and a benchmarking script for speed. The repository publishes a VOS inference script documented with the SAM 2.1 configs and checkpoints (with a flag for LVOS-style datasets) and an SA-V evaluator for the released val and test sets; MOSE and LVOS scores come from those datasets' own evaluation tools or servers.176

What it is useful for

Promptable segmentation of objects in images, automatic mask generation, and segmenting and tracking objects across video frames.1

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.
  • The README requires Python 3.10 or later with PyTorch 2.5.1 and torchvision 0.20.1 or later and notes that installation compiles an optional CUDA extension; it recommends WSL with Ubuntu on Windows.1

Organization context

Other releases in the Segment Anything (SAM) family

  • SAM 3.1Model-disclosure tier (USASI rubric v0.1): Restricted weights

Segment Anything (SAM) family overview

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. headquarters

Developed by Meta's FAIR research group and published in the facebookresearch GitHub organization and the facebook Hugging Face account. Meta Platforms, Inc. has its principal executive offices in Menlo Park, California, per its Form 10-K.1911

Assessed Sep 29, 2026

Sources

  1. 1.
    facebookresearch/sam2 README (external site: github.com)

    Meta (GitHub) · Repository · accessed Sep 29, 2026

  2. 2.
    SAM 2 release notes (external site: github.com)

    Meta (GitHub) · Release notes · accessed Sep 29, 2026

  3. 3.
    facebookresearch/sam2 LICENSE (Apache 2.0) (external site: github.com)

    Meta (GitHub) · License · accessed Sep 29, 2026

  4. 4.
    facebookresearch/sam2 LICENSE_cctorch (external site: github.com)

    Meta (GitHub) · License · accessed Sep 29, 2026

  5. 5.
    Training Code for SAM 2 (training/README.md) (external site: github.com)

    Meta (GitHub) · Documentation · accessed Sep 29, 2026

  6. 6.
    Segment Anything Video (SA-V) Dataset README (external site: github.com)

    Meta (GitHub) · Dataset card · accessed Sep 29, 2026

  7. 7.
  8. 8.
    SAM 2: Segment Anything in Images and Videos (arXiv 2408.00714v2) (external site: arxiv.org)

    arXiv (Meta FAIR authors) · Paper · published Oct 28, 2024 · accessed Sep 29, 2026

  9. 9.
    facebook/sam2.1-hiera-large model card (external site: huggingface.co)

    Meta (Hugging Face) · Model card · accessed Sep 29, 2026

  10. 10.
  11. 11.
    Meta Platforms, Inc. Form 10-K for the fiscal year ended December 31, 2025 (external site: sec.gov)

    Meta Platforms, Inc. (U.S. SEC filing) · Filing · published Jan 29, 2026 · accessed Sep 29, 2026

This listing is not an endorsement, a safety assessment, or a federal approval.

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project