Profile Job Results
Jobs
jpr79onvg
Results Ready
Name
distil_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
11/14/2026, 4:40:43 PM
Options
--qairt_version latestVersions
- ONNX Runtime: 1.30.0
- QNN Execution Provider: 2.5.0
- QAIRT: v2.51.0.260929181845
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.11.06.1
Estimated Inference Time
10.2 ms
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
171
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.03 s | 844‑846 MB |
Subsequent App Load | 560 ms | 176‑504 MB |
Inference | 10.2 ms | 0‑2 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
| num_graph_prepare_threads | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device







