Profile Job Results
Jobs
jpx6zmz9p
Results Ready
Name
real_esrgan_x4plus
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 128, 128, 3]Completion Time
9/14/2025, 2:32:20 AM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.09.05.0
Estimated Inference Time
1.94 s
Estimated Peak Memory Usage
0 ‑ 74 MB
Compute Units
GPU
1816
| Stage | Time | Memory |
|---|---|---|
First App Load | 8.46 min | 196‑198 MB |
Subsequent App Load | 8.36 min | 224‑228 MB |
Inference | 1.94 s | 0‑74 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