# RT-DETRv4-M

> RT-DETRv4-M: 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: 19.0M
- GFLOPs: 57.0
- Default input size: 640px
- Detection: detr · nms-free
- Architecture: transformer · HGNetv2 backbone
- Weight license: Apache-2.0
- Paper-reported mAP@50-95: 53.5%
- 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 | 56.5 | 6.7 | 149.1 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 56.5 | 7.0 | 143.1 | 188 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 56.5 | 23.1 | 43.3 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 56.4 | 15.4 | 65.0 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 56.5 | 56.6 | 17.7 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 56.5 | 33.6 | 29.8 | 189 |
| NVIDIA RTX 5070 Ti | TensorRT FP16 | 56.4 | 86.7 | 11.5 | - |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 56.5 | 84.4 | 11.9 | - |
| Raspberry Pi 5 | ONNX Runtime FP32 | 56.5 | 1.0 | 1006.5 | - |
| Raspberry Pi 5 | PyTorch FP32 | 56.5 | 0.6 | 1588.4 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreRTDETRv4m.pt")
result = model("image.jpg", conf=0.25, iou=0.45)
```

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