Profile Job Results
Jobs
jpy83r24g
Results Ready
Name
bert_base_uncased_hf
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
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
10/3/2026, 2:37:22 PM
Versions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
24.2 ms
Estimated Peak Memory Usage
0 ‑ 260 MB
Compute Units
NPU
537
| Stage | Time | Memory |
|---|---|---|
First App Load | 15.9 s | 593‑594 MB |
Subsequent App Load | 538 ms | 260‑261 MB |
Inference | 24.2 ms | 0‑260 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