Profile Job Results
Jobs
jpyje0k0p
Results Ready
Name
ddcolor
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 256, 256, 3]Completion Time
9/28/2025, 10:08:21 AM
Versions
- TensorFlow Lite: 2.17.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
585 ms
Estimated Peak Memory Usage
94 ‑ 398 MB
Compute Units
CPU
665
GPU
547
| Stage | Time | Memory |
|---|---|---|
First App Load | 45.7 s | 496‑506 MB |
Subsequent App Load | 29.1 s | 200‑512 MB |
Inference | 585 ms | 94‑398 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device