Profile Job Results
Jobs
jp8e8v9zp
Results Ready
Name
grootn15_vlm_proj
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
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
9/20/2026, 4:56:15 AM
Options
--qairt_version latestVersions
- ONNX Runtime: 1.27.1
- QAIRT: v2.50.0.260828221209
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
37.9 ms
Estimated Peak Memory Usage
84 ‑ 87 MB
Compute Units
NPU
195
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.41 s | 472‑473 MB |
Subsequent App Load | 1.51 s | 485‑486 MB |
Inference | 37.9 ms | 84‑87 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