Profile Job Results
Jobs
j5w992r4p
Results Ready
Name
track_anything_float_TrackAnythingEncodeKeyWithoutShrinkage
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.5
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 320, 576, 3]Completion Time
1/31/2026, 7:44:28 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.42.0.251225135753_193295
- QNN TfLite Delegate: v2.42.0.251225135753_193295
- Qualcomm Linux: 1.5-ver.1.1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
12.7 ms
Estimated Peak Memory Usage
20 ‑ 63 MB
Compute Units
NPU
71
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.18 s | 193 MB |
Subsequent App Load | 166 ms | 21‑22 MB |
Inference | 12.7 ms | 20‑63 MB |
| TensorFlow Lite | 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 | kHtpOptimizeForInference |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device