Profile Job Results
Jobs
j5w12nejg
Results Ready
Name
grootn15_vlm_proj
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
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, 3:41:53 PM
Versions
- ONNX Runtime: 1.26.0
- QAIRT: v2.45.0.260326154327
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
54.1 ms
Estimated Peak Memory Usage
21 ‑ 45 MB
Compute Units
NPU
195
| Stage | Time | Memory |
|---|---|---|
First App Load | 444 ms | 493‑494 MB |
Subsequent App Load | 457 ms | 497‑498 MB |
Inference | 54.1 ms | 21‑45 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