# DEIMv2-Femto

> DEIMv2-Femto: transformer object detector from the DEIMv2 family. Available in LibreYOLO, the MIT-licensed open-source library (free for commercial use).

- Family: DEIMv2 (Intellindust AI Lab)
- Parameters: 1.0M
- GFLOPs: 1.7
- Default input size: 416px
- Detection: detr · nms-free
- Architecture: transformer · DINOv3-distilled ViT backbone
- Weight license: Apache-2.0
- Paper-reported mAP@50-95: 31%
- Paper: https://arxiv.org/abs/2509.20787
- Original code: https://github.com/Intellindust-AI-Lab/DEIMv2

## Benchmarks (COCO val2017)

| Hardware | Runtime | mAP@50-95 | FPS | Latency (ms) | VRAM (MB) |
|---|---|---|---|---|---|
| NVIDIA Jetson Orin Nano Super 8GB | ONNX Runtime FP32 | 34.5 | 37.1 | 26.9 | - |
| NVIDIA Jetson Orin Nano Super 8GB | PyTorch FP32 | 34.5 | 14.8 | 67.5 | 29 |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP16 | 34.5 | 65.7 | 15.2 | - |
| NVIDIA Jetson Orin Nano Super 8GB | TensorRT FP32 | 34.5 | 60.0 | 16.7 | - |
| NVIDIA RTX 5070 Ti | ONNX Runtime FP32 | 34.5 | 90.3 | 11.1 | - |
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 34.5 | 45.3 | 22.1 | 33 |
| NVIDIA RTX 5070 Ti | TensorRT FP32 | 34.3 | 119.0 | 8.4 | - |
| Raspberry Pi 5 | ONNX Runtime FP32 | 34.5 | 16.7 | 59.8 | - |
| Raspberry Pi 5 | PyTorch FP32 | 34.5 | 7.4 | 135.3 | - |

## Usage with LibreYOLO

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreDEIMv2femto.pt")
result = model("image.jpg", conf=0.25, iou=0.45)
```

Source: https://www.visionanalysis.org/model/deimv2-femto. Benchmarks produced with LibreYOLO (https://github.com/Libre-YOLO/libreyolo).