# YOLO11-X

> YOLO11-X: one-stage object detector from the YOLO11 family. Planned for LibreYOLO (not yet packaged).

- Family: YOLO11 (External baseline)
- Parameters: 56.9M
- GFLOPs: 194.9
- Default input size: 640px
- Detection: anchor-free · nms
- Architecture: one-stage · CSPDarknet backbone
- Weight license: non-permissive
- Paper-reported mAP@50-95: 54.7%

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 53.6 | 0.6 | 1787.0 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 53.6 | 5.1 | 196.1 | 391 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 53.6 | 15.8 | 63.3 | 14 |
| Raspberry Pi 5 | ncnn FP32 | 53.6 | 0.8 | 1296.7 | - |
| Raspberry Pi 5 | ONNX Runtime FP32 | 53.6 | 0.4 | 2526.0 | - |
| Raspberry Pi 5 | PyTorch FP32 | 53.6 | 0.4 | 2522.8 | - |


Source: https://www.visionanalysis.org/model/yolo11x. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).