Profile Job Results
Jobs
jgo20en4p
Results Ready
Name
sam_SAMDecoder
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_embeddings
: float32[1, 64, 64, 256]point_coords
: float32[1, 2, 2]point_labels
: float32[1, 2]Completion Time
1/22/2025, 12:02:02 AM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.28.2.241116104011_103376
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
8.50 ms
Estimated Peak Memory Usage
0 ‑ 36 MB
Compute Units
NPU
845
Stage | Time | Memory |
---|---|---|
First App Load | 7.52 s | 158‑172 MB |
Subsequent App Load | 5.44 s | 140‑231 MB |
Inference | 8.50 ms | 0‑36 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device