Profile Job Results
Jobs
jp81qj6o5
Results Ready
Name
mobile_bert_uncased_google
Target Device
- Samsung Galaxy S26
- Android 16
- Snapdragon® 8 Elite Gen 5 for Galaxy | SM8850-AD
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
7/25/2026, 6:22:40 PM
Versions
- ONNX Runtime: 1.27.1
- QAIRT: v2.45.0.260326154327
- Android: 16 (BP4A.251205.006)
- AI Hub: aihub-2026.07.17.0
Estimated Inference Time
13.9 ms
Estimated Peak Memory Usage
0 ‑ 186 MB
Compute Units
NPU
1850
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.12 s | 400‑409 MB |
Subsequent App Load | 243 ms | 74‑262 MB |
Inference | 13.9 ms | 0‑186 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" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device







