Profile Job Results
Jobs
j5qlwr9mp
Results Ready
Name
efficientnet_lite4
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 300, 300, 3]Completion Time
9/19/2026, 1:20:19 PM
Options
--qairt_version latestVersions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
4.84 ms
Estimated Peak Memory Usage
0 ‑ 33 MB
Compute Units
NPU
121
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.02 s | 135‑136 MB |
Subsequent App Load | 212 ms | 32 MB |
Inference | 4.84 ms | 0‑33 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