Profile Job Results
Jobs
jpevz7m75
Results Ready
Name
edgetam_EdgeTAMDecoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_embeddings: float32[1, 256, 64, 64]high_res_features1: float32[1, 32, 256, 256]high_res_features2: float32[1, 64, 128, 128]sparse_embedding: float32[1, 3, 256]Completion Time
2/22/2026, 4:48:10 PM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.24.1
- QAIRT: v2.42.0.251225135753_193295
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.02.14.0
Estimated Inference Time
8.42 ms
Estimated Peak Memory Usage
16 ‑ 19 MB
Compute Units
NPU
821
| Stage | Time | Memory |
|---|---|---|
First App Load | 7.95 s | 208‑209 MB |
Subsequent App Load | 217 ms | 26 MB |
Inference | 8.42 ms | 16‑19 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 | "2" |
| 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