# RF-DETR-L

> RF-DETR-L: transformer object detector from the RF-DETR family. Available in LibreYOLO, the MIT-licensed open-source library (free for commercial use).

- Family: RF-DETR (Roboflow)
- Parameters: 33.9M
- GFLOPs: 0.0
- Default input size: 704px
- Detection: detr · nms-free
- Architecture: transformer · DINOv2 backbone
- Weight license: Apache-2.0
- Paper-reported mAP@50-95: 56.5%
- Paper: https://blog.roboflow.com/rf-detr
- Original code: https://github.com/roboflow/rf-detr

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 58.6 | 3.4 | 295.5 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 58.5 | 4.0 | 248.5 | 222 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 58.7 | 8.4 | 119.3 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 58.6 | 7.8 | 127.8 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 58.6 | 43.8 | 22.8 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 58.5 | 25.1 | 39.9 | 223 |
| NVIDIA RTX 5070 Ti | TensorRT FP16 | 58.6 | 47.6 | 21.0 | - |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 58.6 | 45.1 | 22.2 | - |
| Raspberry Pi 5 | ONNX Runtime FP32 | 58.6 | 0.5 | 1924.5 | - |
| Raspberry Pi 5 | PyTorch FP32 | 58.6 | 0.5 | 2110.2 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreRFDETRl.pt")
result = model("image.jpg", conf=0.25, iou=0.45)
```

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