Model weights · YOLO26

Download YOLO26 weights

A single-stage detector that outputs final boxes directly, with no separate NMS cleanup step, so it runs faster on CPUs and edge devices while keeping top accuracy. 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 checkpoints, pick a size and download

A single-stage detector that outputs final boxes directly, with no separate NMS cleanup step, so it runs faster on CPUs and edge devices while keeping top accuracy.

  • YOLO26n
    yolo26n.pt
    COCO mAP
    40.9
    Params
    2.4M
  • YOLO26s
    yolo26s.pt
    COCO mAP
    48.6
    Params
    9.5M
  • YOLO26m
    yolo26m.pt
    COCO mAP
    53.1
    Params
    20.4M
  • YOLO26l
    yolo26l.pt
    COCO mAP
    55.0
    Params
    24.8M
  • YOLO26x
    yolo26x.pt
    COCO mAP
    57.5
    Params
    55.7M

Scores are COCO 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 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.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 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 spans YOLO26n at 2.4M parameters to YOLO26x at 55.7M, 23.2× the model, for 16.6 more COCO mAP (40.9 to 57.5). That works out to roughly 0.31 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 → YOLO26s, worth 1.08 COCO mAP points per million parameters. The worst is YOLO26l → YOLO26x at 0.08, or 13× less efficient, for 30.9M extra parameters and only 2.5 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.

Where it sits in the catalog

Against the 8 families here that publish COCO mAP, YOLO26's best checkpoint ranks 1st at 57.5. Read that as a tier indicator rather than a head-to-head: the families use different size ladders, input sizes and training recipes, and each number is the authors' own. The closest alternatives for object detection are YOLO11, YOLO12 and YOLOv10.

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

YOLO26 is Ultralytics' end-to-end detector. It drops NMS and Distribution Focal Loss (DFL) so the model outputs final predictions directly, which simplifies export and speeds up CPU and edge inference. It keeps the full multi-task head and posts the highest published COCO accuracy of any YOLO here at a comparable size. Weights download automatically on first use, or grab a checkpoint directly below.

Author
Ultralytics
Released
2026
Tasks
Detect, Segment, Semantic segmentation, Depth, Classify, Pose, OBB, Open-vocabulary
Framework
Ultralytics (PyTorch)
Input size
640px
License
AGPL-3.0
Resources
Compare: YOLO26 vs YOLOv8 vs YOLO11DocsGitHubHugging FaceLicense

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 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.pt")`. All 5 YOLO26 checkpoints are hosted officially.
Is YOLO26 free for commercial use?
YOLO26 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 model size should I use?
Start with YOLO26n, 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 57.5 COCO mAP.