Profile Job Results
Jobs
jgk2dv7og
Results Ready
Name
bert_base_uncased_hf
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
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
9/19/2026, 12:25:20 PM
Options
--qairt_version latestVersions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
17.3 ms
Estimated Peak Memory Usage
0 ‑ 4 MB
Compute Units
NPU
537
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.91 s | 680‑681 MB |
Subsequent App Load | 464 ms | 257‑936 MB |
Inference | 17.3 ms | 0‑4 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







