Profile Job Results
Jobs
jpyv64v4p
Results Ready
Name
edgetam_decoder
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
Input Specs
image_embeddings: uint8[1, 256, 64, 64]high_res_features1: uint8[1, 32, 256, 256]high_res_features2: uint8[1, 64, 128, 128]sparse_embedding: uint8[1, 3, 256]Completion Time
5/9/2026, 5:50:04 PM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.24.3
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.04.25.0
Estimated Inference Time
137 ms
Estimated Peak Memory Usage
39 ‑ 65 MB
Compute Units
CPU
1033
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.04 s | 69‑70 MB |
Subsequent App Load | 1.05 s | 71‑72 MB |
Inference | 137 ms | 39‑65 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