Profile Job Results
Jobs
j57dd2qq5
Results Ready
Name
vit_w8a8
Target Device
- Snapdragon 7 Gen 4 QRD
- Android 15
- Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]Completion Time
1/31/2026, 7:10:28 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.42.0.251225135753_193295
- QNN TfLite Delegate: v2.42.0.251225135753_193295
- Android: 15 (AQ3A.250411.001)
- Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
20.2 ms
Estimated Peak Memory Usage
1 ‑ 71 MB
Compute Units
NPU
1381
CPU
240
GPU
10
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.95 s | 283‑290 MB |
Subsequent App Load | 354 ms | 91‑166 MB |
Inference | 20.2 ms | 1‑71 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.optimization_strategy | kHtpOptimizeForInferenceO3 |
| 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