Profile Job Results
Jobs
jgkqekqng
Results Ready
Name
sam2_SAM2Encoder
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 1024, 1024, 3]Completion Time
6/28/2025, 10:34:48 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.34.2.250528164111_119506
- QNN TfLite Delegate: v2.34.2.250528164111_119506
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.06.12.0
Estimated Inference Time
264 ms
Estimated Peak Memory Usage
92 ‑ 117 MB
Compute Units
NPU
593
CPU
54
| Stage | Time | Memory |
|---|---|---|
First App Load | 55.4 s | 1 GB |
Subsequent App Load | 56.2 s | 1‑2 GB |
Inference | 264 ms | 92‑117 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device