Profile Job Results
Jobs
jgj7x1zxg
Results Ready
Name
siglip2_image_encoder
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 224, 224, 3]Completion Time
9/6/2026, 4:31:20 AM
Versions
- Lite RT: 1.4.5
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
12.0 ms
Estimated Peak Memory Usage
0 ‑ 184 MB
Compute Units
NPU
551
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.72 s | 463‑464 MB |
Subsequent App Load | 349 ms | 183‑184 MB |
Inference | 12.0 ms | 0‑184 MB |
| Lite RT | 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