# YOLOv10-M

> YOLOv10-M: one-stage object detector from the YOLOv10 family. Planned for LibreYOLO (not yet packaged).

- Family: YOLOv10 (Tsinghua University)
- Parameters: 15.4M
- GFLOPs: 59.1
- Default input size: 640px
- Detection: anchor-free · nms-free
- Architecture: one-stage · CSPDarknet backbone
- Weight license: non-permissive
- Paper-reported mAP@50-95: 51.1%
- Paper: https://arxiv.org/abs/2405.14458
- Original code: https://github.com/THU-MIG/yolov10

## Benchmarks (COCO val2017)

Not yet benchmarked.


Source: https://www.visionanalysis.org/model/yolov10m. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).