# YOLO11-L

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

- Family: YOLO11 (External baseline)
- Parameters: 25.3M
- GFLOPs: 86.9
- Default input size: 640px
- Detection: anchor-free · nms
- Architecture: one-stage · CSPDarknet backbone
- Weight license: non-permissive
- Paper-reported mAP@50-95: 53.4%

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 52.3 | 1.1 | 874.4 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 52.3 | 9.1 | 109.9 | 224 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 52.3 | 22.6 | 44.3 | 14 |
| Raspberry Pi 5 | ncnn FP32 | 52.3 | 1.5 | 650.1 | - |
| Raspberry Pi 5 | ONNX Runtime FP32 | 52.3 | 0.8 | 1261.7 | - |
| Raspberry Pi 5 | PyTorch FP32 | 52.3 | 0.7 | 1385.3 | - |


Source: https://www.visionanalysis.org/model/yolo11l. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).