Model weights · YOLO26-pose

Download YOLO26-pose weights

Human pose checkpoints: each detected person comes back as 17 COCO keypoints, so posture, ergonomics, rep counting and safety rules become geometry. 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-pose checkpoints, pick a size and download

Human pose checkpoints: each detected person comes back as 17 COCO keypoints, so posture, ergonomics, rep counting and safety rules become geometry.

  • YOLO26n-pose
    yolo26n-pose.pt
    COCO pose mAP
    57.2
    Params
    2.9M
    Size
    7.5 MB
  • YOLO26s-pose
    yolo26s-pose.pt
    COCO pose mAP
    63.0
    Params
    10.4M
    Size
    23 MB
  • YOLO26m-pose
    yolo26m-pose.pt
    COCO pose mAP
    68.8
    Params
    21.5M
    Size
    46.8 MB
  • YOLO26l-pose
    yolo26l-pose.pt
    COCO pose mAP
    70.4
    Params
    25.9M
    Size
    55.3 MB
  • YOLO26x-pose
    yolo26x-pose.pt
    COCO pose mAP
    71.6
    Params
    57.6M
    Size
    120.4 MB

Scores are COCO pose 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-pose 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-pose.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-pose 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-pose spans YOLO26n-pose at 2.9M parameters to YOLO26x-pose at 57.6M, 19.9× the model, for 14.4 more COCO pose mAP (57.2 to 71.6). That works out to roughly 0.26 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-pose → YOLO26s-pose, worth 0.77 COCO pose mAP points per million parameters. The worst is YOLO26l-pose → YOLO26x-pose at 0.04, or 20× less efficient, for 31.7M extra parameters and only 1.2 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-pose

YOLO26-pose returns the 17 COCO keypoints per person rather than just a box, which turns anything that depends on how a body is arranged into a geometry problem you can write rules against: whether someone is bent at the waist, how many repetitions they completed, whether they crossed a line facing the machine or away from it. The scores here are keypoint mAP on COCO val2017 and are not comparable with the box mAP the detection families publish, so the two are ranked separately across this catalog.

Author
Ultralytics
Released
2026
Tasks
Pose
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-pose 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-pose.pt")`. All 5 YOLO26-pose checkpoints are hosted officially.
Is YOLO26-pose free for commercial use?
YOLO26-pose 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-pose model size should I use?
Start with YOLO26n-pose, 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 71.6 COCO mAP.