Profile Job Results
Jobs
jglwm77mp
Results Ready
Name
electra_bert_base_discrim_google
Target Device
- Snapdragon X2 Elite CRD
- Windows 11
- Snapdragon® X2 Elite | SC8480XP
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]attention_masks: float32[1, 384]Completion Time
10/3/2026, 8:31:33 PM
Versions
- ONNX Runtime: 1.30.0
- QAIRT: v2.50.0.260828221209
- Windows: Windows 11 (28000)
- Build ID: APSS.WP_GL.1.0.r0-05000-SC8480XRELSFNWZA-4
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
6.66 ms
Estimated Peak Memory Usage
1 MB
Compute Units
NPU
339
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.01 s | 1 GB |
Subsequent App Load | 1.37 s | 25 MB |
Inference | 6.66 ms | 1 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







