Profile Job Results
Jobs
jgd3jm2ep
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
mask_indices: int32[1]attention_masks: uint16[1, 384]input_tokens: int32[1, 384]Completion Time
9/5/2026, 2:38:46 PM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
11.4 ms
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
409
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.69 s | 607‑608 MB |
Subsequent App Load | 256 ms | 0‑272 MB |
Inference | 11.4 ms | 0‑2 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device







