Profile Job Results
Jobs
jpv90xk75
Results Ready
Name
grootn15_vlm_proj
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
vlm_embeds: float32[1, 384, 2048]vlm_attention_mask: float32[1, 32, 384, 384]Completion Time
7/4/2026, 11:41:58 AM
Versions
- ONNX Runtime: 1.26.0
- QAIRT: v2.45.0.260326154327
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
30.6 ms
Estimated Peak Memory Usage
100 ‑ 112 MB
Compute Units
NPU
195
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.01 s | 493‑499 MB |
Subsequent App Load | 902 ms | 485‑496 MB |
Inference | 30.6 ms | 100‑112 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