# YOLO26-X

> YOLO26-X: one-stage object detector from the yolo26 family. Planned for LibreYOLO (not yet packaged).

- Family: yolo26
- Parameters: 55.7M
- GFLOPs: 193.9
- Default input size: 640px
- Detection: anchor-free · nms-free
- Architecture: one-stage · CSPDarknet backbone
- Weight license: non-permissive
- Paper-reported mAP@50-95: 57.5%

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 56.5 | 63.9 | 15.6 | 386 |
| Raspberry Pi 5 | PyTorch FP32 | 60.2 | 0.4 | 2507.6 | - |


Source: https://www.visionanalysis.org/model/yolo26x. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).