Profile Job Results
Jobs
jp3rx64mp
Results Ready
Name
owl_vit
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
pixel_values: float32[1, 3, 768, 768]input_ids: int32[1, 16]attention_mask: int32[1, 16]Completion Time
11/15/2026, 3:08:35 PM
Options
--qairt_version latestVersions
- Lite RT: 1.4.2
- QAIRT: v2.51.0.260929181845
- QNN TfLite Delegate: v2.51.0.260929181845
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.11.06.1
Estimated Inference Time
36.8 ms
Estimated Peak Memory Usage
0 ‑ 311 MB
Compute Units
NPU
1226
CPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 37.8 s | 862‑863 MB |
Subsequent App Load | 343 ms | 304‑305 MB |
Inference | 36.8 ms | 0‑311 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device







