Profile Job Results
Jobs
jgd261rz5
Results Ready
Name
mobile_bert_uncased_google
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]attention_masks: float32[1, 384]mask_indices: int32[1]Completion Time
8/8/2026, 4:58:55 PM
Versions
- Lite RT: 1.4.5
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
25.0 ms
Estimated Peak Memory Usage
0 ‑ 82 MB
Compute Units
NPU
1081
| Stage | Time | Memory |
|---|---|---|
First App Load | 10.5 s | 328‑329 MB |
Subsequent App Load | 264 ms | 82‑83 MB |
Inference | 25.0 ms | 0‑82 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