Profile Job Results
Jobs
jgj3n1q1p
Results Ready
Name
owl_vit
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
pixel_values: float32[1, 3, 768, 768]input_ids: int32[1, 16]attention_mask: int32[1, 16]Completion Time
10/3/2026, 10:19:14 PM
Versions
- ONNX Runtime: 1.30.0
- QAIRT: v2.50.0.260828221209
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
51.1 ms
Estimated Peak Memory Usage
6 ‑ 16 MB
Compute Units
NPU
770
CPU
3
| Stage | Time | Memory |
|---|---|---|
First App Load | 21.1 s | 1 GB |
Subsequent App Load | 576 ms | 313‑314 MB |
Inference | 51.1 ms | 6‑16 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