Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Track-Anything

Profile Job Results

Jobs
jpvzqrq7g
Results Ready
Name
track_anything_encode_value
Target Device
  • Snapdragon 8 Elite Gen 5 QRD
  • Android 16
  • Snapdragon® 8 Elite Gen 5 | SM8850
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 320, 576, 3]
mask: float32[1, 320, 576]
f16: float32[1, 1024, 20, 36]
hidden_state: float32[1, 1, 64, 20, 36]
Completion Time
5/3/2026, 12:26:01 AM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 16 (BQ2A.251217.002-BP2A.250705.008)
  • Build ID: Kaanapali.LA.1.0.r1-01100-STD.PROD-1
  • AI Hub: aihub-2026.04.25.0
Estimated Inference Time
5.33 ms
Estimated Peak Memory Usage
3 ‑ 202 MB
Compute Units
NPU
110
StageTimeMemory
First App Load
1.75 s297‑304 MB
Subsequent App Load
102 ms45‑245 MB
Inference
5.33 ms3‑202 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