Profile Job Results
Jobs
j57jk3x95
Results Ready
Name
deeplab_xception
Target Device
- Dragonwing Q-6690 MTP
- Android 15
- Qualcomm® Dragonwing™ Q-6690 | QCM6690
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 480, 520, 3]Completion Time
4/5/2026, 8:35:44 PM
Versions
- LiteRT: 1.4.2
- QAIRT: v2.43.0.260127150333_193827
- QNN TfLite Delegate: v2.43.0.260127150333_193827
- Android: 15 (AQ3A.250330.001)
- Build ID: QCM6690.LA.1.0.r1-00117-STD.PROD-1
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
90.9 ms
Estimated Peak Memory Usage
0 ‑ 295 MB
Compute Units
NPU
205
| Stage | Time | Memory |
|---|---|---|
First App Load | 21.5 s | 280‑287 MB |
Subsequent App Load | 246 ms | 90‑390 MB |
Inference | 90.9 ms | 0‑295 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device