Profile Job Results
Jobs
jgje60y85
Results Ready
Name
resnet_3d_w8a8
Target Device
- RB5 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: uint8[1, 16, 112, 112, 3]Completion Time
12/13/2025, 9:33:47 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.12.07.0
Estimated Inference Time
1.36 s
Estimated Peak Memory Usage
1 GB
Compute Units
CPU
105
GPU
3
| Stage | Time | Memory |
|---|---|---|
First App Load | 250 ms | 9‑11 MB |
Subsequent App Load | 138 ms | 7‑10 MB |
Inference | 1.36 s | 1 GB |
| TensorFlow Lite | 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device