Profile Job Results
Jobs
j5m6yze7g
Results Ready
Name
vit_w8a8
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]Completion Time
10/4/2025, 8:03:17 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.38.0.250901140452_125126
- QNN TfLite Delegate: v2.38.0.250901140452_125126
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.09.26.0
Estimated Inference Time
60.3 ms
Estimated Peak Memory Usage
2 ‑ 45 MB
Compute Units
NPU
1382
CPU
241
GPU
10
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.51 s | 389‑400 MB |
Subsequent App Load | 5.45 s | 278‑416 MB |
Inference | 60.3 ms | 2‑45 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
| 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