Profile Job Results
Jobs
j5wd84y3g
Results Ready
Name
track_anything_segment
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
f16: float32[1, 1024, 20, 36]f8: float32[1, 512, 40, 72]f4: float32[1, 256, 80, 144]memory_readout: float32[1, 1, 512, 20, 36]hidden_state: float32[1, 1, 64, 20, 36]Completion Time
4/5/2026, 9:33:36 AM
Versions
- LiteRT: 1.4.2
- QAIRT: v2.43.0.260127150333_193827
- QNN TfLite Delegate: v2.43.0.260127150333_193827
- Android: 14 (UAG2.240908.001)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
33.6 ms
Estimated Peak Memory Usage
2 ‑ 195 MB
Compute Units
NPU
120
| Stage | Time | Memory |
|---|---|---|
First App Load | 12.6 s | 241‑247 MB |
Subsequent App Load | 453 ms | 59‑253 MB |
Inference | 33.6 ms | 2‑195 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
| htp_options.device_id | 1 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device