Profile Job Results
Jobs
jp2r4mzrg
Results Ready
Name
wedetect_text_encoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[80, 16]attention_mask: int32[80, 16]Completion Time
9/20/2026, 12:22:11 PM
Options
--qairt_version latestVersions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
93.8 ms
Estimated Peak Memory Usage
0 ‑ 552 MB
Compute Units
NPU
572
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.63 min | 4 GB |
Subsequent App Load | 691 ms | 552‑553 MB |
Inference | 93.8 ms | 0‑552 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