Profile Job Results
Jobs
jgd3j23rp
Results Ready
Name
albert_base_v2_hf
Target Device
- Samsung Galaxy S22 5G
- Android 12
- Snapdragon® 8 Gen 1 | SM8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]attention_masks: uint16[1, 384]mask_indices: int32[1]Completion Time
9/5/2026, 9:59:45 AM
Versions
- ONNX Runtime: 1.27.1
- QAIRT: v2.45.0.260326154327
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
22.2 ms
Estimated Peak Memory Usage
0 ‑ 315 MB
Compute Units
NPU
485
| Stage | Time | Memory |
|---|---|---|
First App Load | 15.0 s | 409‑418 MB |
Subsequent App Load | 398 ms | 21‑338 MB |
Inference | 22.2 ms | 0‑315 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