Profile Job Results
Jobs
jg9m4d485
Results Ready
Name
openai_clip
Target Device
- Snapdragon 7 Gen 4 QRD
- Android 15
- Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint16[1, 3, 224, 224]text: int32[1, 5, 77]Completion Time
8/22/2026, 8:46:40 PM
Options
--onnx_execution_providers qnnVersions
- ONNX Runtime: 1.27.1
- QAIRT: v2.45.0.260326154327
- Android: 15 (AQ3A.250411.001)
- Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
37.9 ms
Estimated Peak Memory Usage
1 ‑ 669 MB
Compute Units
NPU
1052
CPU
3
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.02 min | 1 GB |
Subsequent App Load | 350 ms | 173‑842 MB |
Inference | 37.9 ms | 1‑669 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 | "0" |
| 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