# RT-DETRv4-L

> RT-DETRv4-L: transformer object detector from the RT-DETRv4 family. Available in LibreYOLO, the MIT-licensed open-source library (free for commercial use).

- Family: RT-DETRv4 (Intellindust AI Lab)
- Parameters: 31.0M
- GFLOPs: 91.0
- Default input size: 640px
- Detection: detr · nms-free
- Architecture: transformer · HGNetv2 backbone
- Weight license: Apache-2.0
- Paper-reported mAP@50-95: 55.4%
- Paper: https://arxiv.org/abs/2510.25257
- Original code: https://arxiv.org/abs/2510.25257

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 57.8 | 4.8 | 206.5 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 57.8 | 4.7 | 210.8 | 246 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 57.8 | 18.1 | 55.2 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 57.8 | 12.1 | 82.4 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 57.8 | 48.0 | 20.8 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 57.8 | 24.7 | 40.4 | 245 |
| NVIDIA RTX 5070 Ti | TensorRT FP16 | 57.7 | 78.0 | 12.8 | - |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 57.8 | 72.7 | 13.8 | - |
| Raspberry Pi 5 | ONNX Runtime FP32 | 57.8 | 0.7 | 1427.4 | - |
| Raspberry Pi 5 | PyTorch FP32 | 57.8 | 0.4 | 2303.8 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreRTDETRv4l.pt")
result = model("image.jpg", conf=0.25, iou=0.45)
```

Source: https://www.visionanalysis.org/model/rtdetrv4-l. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).