Domain
Task
All TasksImage Classification (1,593)3D Object Detection (743)Text Embedding (472)Vision-Language (285)Code Generation (125)Object Detection (106)Speech Recognition (67)Video Understanding (49)Text Generation (48)Segmentation (34)UI Understanding (14)Speech (13)Pose Estimation (11)Super Resolution (10)driver assistance (9)Font Identification (7)image editing (6)Depth Estimation (6)audio generation (6)image generation (4)robotics (3)image to text (2)video object tracking (2)gaze estimation (1)video generation (1)voice activity detection (1)
Showing 10 models
| # | Model | Domain | Task | Params ↑ | GFLOPs | VRAM | Score | Speed | Arch | Source |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | SINet | Edge/Mobile | Segmentation | 0.09M | — | 0 MB | —— | — | — | Qualcomm AI Hub |
| 2 | MediaPipe-Selfie-Segmentation | Edge/Mobile | Segmentation | 0.11M | — | 0 MB | —— | — | — | Qualcomm AI Hub |
| 3 | YOLO26-Segmentation | Edge/Mobile | Segmentation | 2.70M | — | 6 MB | —— | — | — | Qualcomm AI Hub |
| 4 | YOLOv11-Segmentation | Edge/Mobile | Segmentation | 2.89M | — | 7 MB | —— | — | — | Qualcomm AI Hub |
| 5 | YOLOv8-Segmentation | Edge/Mobile | Segmentation | 3.43M | — | 8 MB | —— | — | — | Qualcomm AI Hub |
| 6 | Segformer-Base | Edge/Mobile | Segmentation | 3.75M | — | 5 MB | —— | — | — | Qualcomm AI Hub |
| 7 | DeepLabV3-Plus-MobileNet | Edge/Mobile | Segmentation | 5.80M | — | 14 MB | —— | — | — | Qualcomm AI Hub |
| 8 | DDRNet23-Slim | Edge/Mobile | Segmentation | 6.13M | — | 7 MB | —— | — | — | Qualcomm AI Hub |
| 9 | SalsaNext | Edge/Mobile | Segmentation | 6.71M | — | 16 MB | —— | — | — | Qualcomm AI Hub |
| 10 | PidNet | Edge/Mobile | Segmentation | 8.06M | — | 10 MB | —— | — | — | Qualcomm AI Hub |