Profile Job Results
Jobs
jgod6y1d5
Results Ready
Name
grootn15_vlm_proj
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
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
10/4/2026, 9:59:24 AM
Versions
- ONNX Runtime: 1.30.0
- QAIRT: v2.50.0.260828221209
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
56.7 ms
Estimated Peak Memory Usage
21 ‑ 46 MB
Compute Units
NPU
195
| Stage | Time | Memory |
|---|---|---|
First App Load | 698 ms | 494‑495 MB |
Subsequent App Load | 696 ms | 494‑495 MB |
Inference | 56.7 ms | 21‑46 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