Model weights · YOLOv10

Download YOLOv10 weights

The first widely used YOLO that skips the NMS post-processing step, using paired training heads so inference is truly end to end and low latency. Pick a size below and download the official .pt checkpoint in one click, with published COCO accuracy, size and license all in view.

AGPL-3.0Tsinghua University (THU-MIG) · 2024 · Built on Ultralytics (PyTorch)

YOLOv10 checkpoints, pick a size and download

The first widely used YOLO that skips the NMS post-processing step, using paired training heads so inference is truly end to end and low latency.

  • YOLOv10n
    yolov10n.pt
    COCO mAP
    38.5
    Params
    2.3M
  • YOLOv10s
    yolov10s.pt
    COCO mAP
    46.3
    Params
    7.2M
  • YOLOv10m
    yolov10m.pt
    COCO mAP
    51.1
    Params
    15.4M
  • YOLOv10b
    yolov10b.pt
    COCO mAP
    52.5
    Params
    19.1M
  • YOLOv10l
    yolov10l.pt
    COCO mAP
    53.2
    Params
    24.4M
  • YOLOv10x
    yolov10x.pt
    COCO mAP
    54.4
    Params
    29.5M

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 YOLOv10 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("yolov10n.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 YOLOv10 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

YOLOv10 spans YOLOv10n at 2.3M parameters to YOLOv10x at 29.5M, 12.8× the model, for 15.9 more COCO mAP (38.5 to 54.4). That works out to roughly 0.58 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 Tsinghua University (THU-MIG) at 640px, not re-measured here.

Where the ladder stops paying

The best value step is YOLOv10n → YOLOv10s, worth 1.59 COCO mAP points per million parameters. The worst is YOLOv10b → YOLOv10l at 0.13, or 12× less efficient, for 5.3M extra parameters and only 0.7 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, YOLOv10's best checkpoint ranks 6th at 54.4, against 57.5 for YOLO26. 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 YOLO26, YOLO11 and YOLO12.

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 YOLOv10

YOLOv10 (Tsinghua University, NeurIPS 2024) introduced consistent dual assignments, a one-to-many head for training and a one-to-one head for NMS-free inference, making it the first widely used end-to-end YOLO. It is detection-only, but its efficiency-first design gives strong accuracy at low parameter counts and latency.

Author
Tsinghua University (THU-MIG)
Released
2024
Tasks
Detect
Framework
Built on Ultralytics (PyTorch)
Input size
640px
License
AGPL-3.0
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 YOLOv10 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("yolov10n.pt")`. All 6 YOLOv10 checkpoints are hosted officially.
Is YOLOv10 free for commercial use?
YOLOv10 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 YOLOv10 model size should I use?
Start with YOLOv10n, 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 54.4 COCO mAP.