Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Sequencer2D

Profile Job Results

Jobs
jpv9v01m5
Results Ready
Name
sequencer2d
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 224, 224, 3]
Completion Time
7/7/2026, 3:16:40 AM
Versions
  • LiteRT: 1.4.4
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.07.02.0
Estimated Inference Time
16.6 ms
Estimated Peak Memory Usage
0 ‑ 9 MB
Compute Units
NPU
17670
StageTimeMemory
First App Load
1.45 min785‑786 MB
Subsequent App Load
471 ms81‑535 MB
Inference
16.6 ms0‑9 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue

Sign up to run this model on a hosted Qualcomm® device!

Run on device