Profile Job Results
Jobs
j57xen89g
Results Ready
Name
convnext_base_float
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 224, 224, 3]Completion Time
11/30/2025, 6:21:04 AM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.40.0.251030114326_189385
- QNN TfLite Delegate: v2.40.0.251030114326_189385
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.11.18.0
Estimated Inference Time
5.59 ms
Estimated Peak Memory Usage
0 ‑ 244 MB
Compute Units
NPU
598
| Stage | Time | Memory |
|---|---|---|
First App Load | 7.74 s | 2 GB |
Subsequent App Load | 7.72 s | 2 GB |
Inference | 5.59 ms | 0‑244 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