Profile Job Results
Jobs
jp18elklg
Results Ready
Name
stable_diffusion_v2_1_w8a16_text_encoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.5
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
tokens: int32[1, 77]Completion Time
1/31/2026, 4:44:34 PM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- QAIRT: v2.37.1.250807093845_124904
- Qualcomm Linux: 1.5-ver.1.1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
7.59 ms
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
811
| Stage | Time | Memory |
|---|---|---|
First App Load | 337 ms | 389‑390 MB |
Subsequent App Load | 365 ms | 389‑390 MB |
Inference | 7.59 ms | 0‑3 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