Model weights · SAM 2.1

Download SAM 2.1 weights

A promptable segmentation model with video memory: one click, box or mask segments an object and tracks it across frames in real time. Pick a size below and download the official .pt checkpoint in one click, with published parameters, size and license all in view.

Apache-2.0AGPL-3.0 via UltralyticsMeta AI · 2024 · Ultralytics (PyTorch)

SAM 2.1 checkpoints, pick a size and download

A promptable segmentation model with video memory: one click, box or mask segments an object and tracks it across frames in real time.

Using it with the Ultralytics package?

The SAM 2.1 weights are Apache-2.0, but the Ultralytics package that most people load them with is AGPL-3.0. Running SAM 2.1 through Ultralytics puts your own project under AGPL-3.0 too, which means publishing your source if you distribute it or offer it over a network. An Ultralytics Enterprise license removes that. The Apache-2.0 terms only cover you if you run the weights outside the Ultralytics package.

  • SAM 2.1 tiny
    sam2.1_t.pt
    Params
    38.9M
    Size
    78 MB
  • SAM 2.1 small
    sam2.1_s.pt
    Params
    46M
  • SAM 2.1 base+
    sam2.1_b.pt
    Params
    80.8M
    Size
    162 MB
  • SAM 2.1 large
    sam2.1_l.pt
    Params
    224.4M

Figures are published by the authors. Weights host: github.com. Clicking Download verifies the file and starts it straight from the official CDN.

How to load SAM 2.1 weights

Install the Ultralytics package, then point the loader at the checkpoint. It downloads automatically on first use, or you can pass the local path to the file you downloaded above.

pip install ultralytics
from ultralytics import SAM

# Downloads on first use, or pass a local path to your .pt file
model = SAM("sam2.1_t.pt")
results = model("image.jpg")

Want to see the architecture? Export to ONNX and open it in the ONNX visualizer for a labelled diagram with shapes and parameter counts.

Open visualizer →

Choosing a SAM 2.1 checkpoint

Read off the table above: what each step up the size ladder costs and returns for this family specifically, where it stops being worth it, and what the license actually permits.

What the size ladder buys

SAM 2.1 ships 4 checkpoints, from SAM 2.1 tiny at 38.9M parameters to SAM 2.1 large at 224.4M, 5.8× the model. These are promptable models with no single comparable accuracy figure, so the table lists parameters and download size rather than inventing one. Size and throughput are the axis you choose on: pick the smallest checkpoint that holds up on your own data rather than the largest you can fit.

Licensing, in practice

The weights are Apache-2.0. More importantly, the usual way to run SAM 2.1 is through the `ultralytics` package, which is AGPL-3.0, and that reaches your application even though the weights themselves are not. A permissive badge on the weights is not permission to ship closed-source over that path. Apache-2.0 on the weights is commercial-friendly and needs only attribution.

About SAM 2.1

SAM 2 (Meta AI) extends the Segment Anything model to video with a streaming memory, so a single click, box or mask prompt segments and tracks objects across frames in real time. The 2.1 checkpoints below are the latest, most accurate release, integrated into Ultralytics with permissive Apache-2.0 licensing.

Author
Meta AI
Released
2024
Tasks
Segment, Track
Framework
Ultralytics (PyTorch)
Input size
1024px
License
Apache-2.0
Resources
DocsGitHubPaperLicense

More model weights to download

Each page lists every checkpoint with accuracy, parameters, license and a one-click download.

See all 19 model families →

YOLO tracker FPS benchmarks →Get in touch →
Blog

From the blog

Tutorials, code, and notes on computer vision, deep learning, and applied AI.

View all posts →

Frequently asked questions

How do I download SAM 2.1 weights?
Click the Download button next to any variant in the table above; we verify the file and start it straight from the official CDN. You can also let the loader fetch it automatically on first use with `model = SAM("sam2.1_t.pt")`. All 4 SAM 2.1 checkpoints are hosted officially.
Is SAM 2.1 free for commercial use?
SAM 2.1 is released under Apache-2.0. Apache-2.0 is permissive and commercial-friendly: you can use it in closed-source products with attribution. Always confirm against the linked license text.
Which SAM 2.1 model size should I use?
Start with SAM 2.1 tiny, the smallest and fastest, ideal for prototyping, edge and CPU. Move up the ladder only when you need more accuracy and have the compute for it.