Profile Job Results
Jobs
jp0jrm2ng
Results Ready
Name
owl_vit
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
attention_mask: int32[1, 16]input_ids: int32[1, 16]pixel_values: uint16[1, 3, 768, 768]Completion Time
8/22/2026, 10:01:27 PM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
94.3 ms
Estimated Peak Memory Usage
1 ‑ 7 MB
Compute Units
NPU
907
| Stage | Time | Memory |
|---|---|---|
First App Load | 41.4 s | 1 GB |
Subsequent App Load | 280 ms | 2 MB |
Inference | 94.3 ms | 1‑7 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device