Profile Job Results
Jobs
jpymom00p
Results Ready
Name
pi05_token_emb
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
lang_tokens: int32[1, 200]lang_mask: float32[1, 200]img_embed1: float32[1, 256, 2048]img_embed2: float32[1, 256, 2048]img_embed3: float32[1, 256, 2048]Completion Time
8/8/2026, 8:11:37 AM
Versions
- ONNX Runtime: 1.27.1
- QAIRT: v2.45.0.260326154327
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
2.75 ms
Estimated Peak Memory Usage
0 ‑ 10 MB
Compute Units
NPU
34
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.94 s | 1 GB |
Subsequent App Load | 2.16 s | 1,008‑1,016 MB |
Inference | 2.75 ms | 0‑10 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 |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device