Profile Job Results
Jobs
jgdd79xlg
Results Ready
Name
sam3_head
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
backbone_fpn_0: float32[1, 256, 288, 288]tokenized: int32[1, 32]backbone_fpn_2: float32[1, 256, 72, 72]backbone_fpn_1: float32[1, 256, 144, 144]Completion Time
9/19/2026, 9:55:13 AM
Options
--qairt_version latestVersions
- ONNX Runtime: 1.27.1
- QAIRT: v2.50.0.260828221209
- Android: 16 (BP4A.251205.006)
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
230 ms
Estimated Peak Memory Usage
130 ‑ 142 MB
Compute Units
NPU
2301
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.29 s | 780‑789 MB |
Subsequent App Load | 1.22 s | 774‑785 MB |
Inference | 230 ms | 130‑142 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