Profile Job Results
Jobs
jp0jy0jeg
Results Ready
Name
efficientnet_b4
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 380, 380, 3]Completion Time
9/5/2026, 9:09:35 PM
Versions
- Lite RT: 1.4.5
- Android: 14 (UAG2.240908.001)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
66.0 ms
Estimated Peak Memory Usage
0 ‑ 29 MB
Compute Units
GPU
481
| Stage | Time | Memory |
|---|---|---|
First App Load | 15.3 s | 168‑174 MB |
Subsequent App Load | 1.21 s | 136‑172 MB |
Inference | 66.0 ms | 0‑29 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
Sign up to run this model on a hosted Qualcomm® device!
Run on device