Profile Job Results
Jobs
jg98j6rqp
Results Ready
Name
pi05_backbone
Target Device
- Snapdragon X2 Elite CRD
- Windows 11
- Snapdragon® X2 Elite | SC8480XP
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
hidden_state: float32[1, 968, 2048]prefix_att_2d_masks: float32[1, 1, 968, 968]rope_emb_sin: float32[1, 968, 1, 128]rope_emb_cos: float32[1, 968, 1, 128]Completion Time
5/30/2026, 8:08:45 AM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.25.0
- QAIRT: v2.42.0.251225135753_193295
- Windows: Windows 11 (28000)
- Build ID: APSS.WP_GL.1.0.r0-05000-SC8480XRELSFNWZA-4
- AI Hub: aihub-2026.05.27.0
Estimated Inference Time
252 ms
Estimated Peak Memory Usage
130 MB
Compute Units
NPU
2475
| Stage | Time | Memory |
|---|---|---|
First App Load | 656 ms | 27 MB |
Subsequent App Load | 600 ms | 26 MB |
Inference | 252 ms | 130 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