Model weights · YOLO26-seg

Download YOLO26-seg weights

Instance segmentation checkpoints: every detection comes back with a per-object mask instead of a rectangle, so area, shape and precise redaction are all measurable. Pick a size below and download the official .pt checkpoint in one click, with published COCO accuracy, size and license all in view.

AGPL-3.0Ultralytics · 2026 · Ultralytics (PyTorch)

YOLO26-seg checkpoints, pick a size and download

Instance segmentation checkpoints: every detection comes back with a per-object mask instead of a rectangle, so area, shape and precise redaction are all measurable.

  • YOLO26n-seg
    yolo26n-seg.pt
    COCO mask mAP
    33.9
    Params
    2.7M
    Size
    6.4 MB
  • YOLO26s-seg
    yolo26s-seg.pt
    COCO mask mAP
    40.0
    Params
    10.4M
    Size
    22.4 MB
  • YOLO26m-seg
    yolo26m-seg.pt
    COCO mask mAP
    44.1
    Params
    23.6M
    Size
    52.2 MB
  • YOLO26l-seg
    yolo26l-seg.pt
    COCO mask mAP
    45.5
    Params
    28M
    Size
    60.7 MB
  • YOLO26x-seg
    yolo26x-seg.pt
    COCO mask mAP
    47.0
    Params
    62.8M
    Size
    135.5 MB

Scores are COCO mask mAP at 640px, published by the authors. Weights host: github.com. Clicking Download verifies the file and starts it straight from the official CDN.

How to load YOLO26-seg 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 YOLO

# Downloads on first use, or pass a local path to your .pt file
model = YOLO("yolo26n-seg.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 YOLO26-seg 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

YOLO26-seg spans YOLO26n-seg at 2.7M parameters to YOLO26x-seg at 62.8M, 23.3× the model, for 13.1 more COCO mask mAP (33.9 to 47.0). That works out to roughly 0.22 points per additional million parameters across the whole range, and the return is front-loaded: the early steps are much cheaper than the last one. Published figures from Ultralytics at 640px, not re-measured here.

Where the ladder stops paying

The best value step is YOLO26n-seg → YOLO26s-seg, worth 0.79 COCO mask mAP points per million parameters. The worst is YOLO26l-seg → YOLO26x-seg at 0.04, or 18× less efficient, for 34.8M extra parameters and only 1.5 more points. If you are latency- or memory-bound, that is the step to skip; if you are accuracy-bound and the compute is free, it is the only place left to get it.

Licensing, in practice

The weights are AGPL-3.0. AGPL-3.0 is free for open-source, research and internal use; a closed-source commercial product needs an Ultralytics Enterprise license.

About YOLO26-seg

YOLO26-seg is the segmentation head of the current Ultralytics generation, published as its own set of checkpoints with the -seg suffix. It predicts a mask per instance alongside the box, which is what you need when a rectangle is the wrong shape for the job: measuring the area a spill covers, cutting an object cleanly out of a frame, or blurring only the pixels a face actually occupies rather than the box around it. The mask score is always lower than the box score on the same checkpoint, and that gap is the honest cost of the finer output, not a weaker model.

Author
Ultralytics
Released
2026
Tasks
Segment
Framework
Ultralytics (PyTorch)
Input size
640px
License
AGPL-3.0
Resources
DocsGitHubLicense

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 YOLO26-seg 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 = YOLO("yolo26n-seg.pt")`. All 5 YOLO26-seg checkpoints are hosted officially.
Is YOLO26-seg free for commercial use?
YOLO26-seg is released under AGPL-3.0. That is free for open-source and research; closed-source commercial deployments need an Ultralytics Enterprise license. Always confirm against the linked license text.
Which YOLO26-seg model size should I use?
Start with YOLO26n-seg, 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. The largest variant reaches 47 COCO mAP.