Profile Job Results
Jobs
jp3e2yjz5
Results Ready
Name
resnext101_w8a8
Target Device
- RB5 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]Completion Time
1/10/2026, 9:04:28 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
75.3 ms
Estimated Peak Memory Usage
0 ‑ 539 MB
Compute Units
GPU
150
| Stage | Time | Memory |
|---|---|---|
First App Load | 8.77 s | 1,003‑1,007 MB |
Subsequent App Load | 947 ms | 684‑687 MB |
Inference | 75.3 ms | 0‑539 MB |
| 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device