Profile Job Results
Jobs
j5qe4em75
Results Ready
Name
stable_diffusion_v1_5_w8a16_quantized_VaeDecoderQuantizable
Target Device
- Samsung Galaxy S23
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
latent: uint16[1, 64, 64, 4]Completion Time
5/20/2025, 7:45:09 AM
Options
--qairt_version latestVersions
- ONNX Runtime: 1.21.1
- QAIRT: v2.33.2.250410134701_117956
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.05.14.0
Estimated Inference Time
269 ms
Estimated Peak Memory Usage
0 ‑ 66 MB
Compute Units
NPU
173
| Stage | Time | Memory |
|---|---|---|
First App Load | 436 ms | 67‑68 MB |
Subsequent App Load | 329 ms | 62‑64 MB |
Inference | 269 ms | 0‑66 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device