Profile Job Results
Jobs
jpx11l2lg
Results Ready
Name
gkt_w8a16_mixed_fp16
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint16[1, 6, 3, 224, 480]inv_intrinsics: uint16[1, 6, 3, 3]inv_extrinsics: uint16[1, 6, 4, 4]intrinsics: uint16[1, 6, 3, 3]extrinsics: uint16[1, 6, 4, 4]Completion Time
2/1/2026, 8:12:15 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- QAIRT: v2.37.1.250807093845_124904
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
95.5 ms
Estimated Peak Memory Usage
6 ‑ 14 MB
Compute Units
NPU
624
| Stage | Time | Memory |
|---|---|---|
First App Load | 267 ms | 17‑23 MB |
Subsequent App Load | 203 ms | 1‑9 MB |
Inference | 95.5 ms | 6‑14 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