Profile Job Results
Jobs
jgl398ymg
Results Ready
Name
efficientformer_w8a16
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 3, 224, 224]Completion Time
12/14/2025, 5:34:27 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2025.12.07.0
Estimated Inference Time
139 ms
Estimated Peak Memory Usage
20 ‑ 27 MB
Compute Units
CPU
641
| Stage | Time | Memory |
|---|---|---|
First App Load | 420 ms | 31‑32 MB |
Subsequent App Load | 418 ms | 30‑31 MB |
Inference | 139 ms | 20‑27 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device