Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
EdgeTAM

Profile Job Results

Jobs
jgl72djl5
Results Ready
Name
edgetam_encoder
Target Device
  • SA8775P ADP
  • Android 14
  • Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 1024, 1024, 3]
unnorm_coords: float32[1, 2, 2]
labels: float32[1, 2]
Completion Time
5/31/2026, 5:53:33 PM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 14 (UAG2.240908.001)
  • Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
  • AI Hub: aihub-2026.05.27.0
Estimated Inference Time
27.6 ms
Estimated Peak Memory Usage
20 ‑ 285 MB
Compute Units
NPU
291
StageTimeMemory
First App Load
20.5 s319‑324 MB
Subsequent App Load
381 ms13‑280 MB
Inference
27.6 ms20‑285 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue
htp_options.device_id1

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

Run on device