Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
EdgeTAM

Profile Job Results

Jobs
jgl72dnl5
Results Ready
Name
edgetam_video_decoder
Target Device
  • QCS8450 (Proxy)
  • Android 13
  • Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_embeddings: float32[1, 64, 64, 256]
high_res_features1: float32[1, 256, 256, 32]
high_res_features2: float32[1, 128, 128, 64]
sparse_embedding: float32[1, 3, 256]
Completion Time
5/31/2026, 5:57:35 PM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.05.27.0
Estimated Inference Time
9.39 ms
Estimated Peak Memory Usage
0 ‑ 231 MB
Compute Units
NPU
841
StageTimeMemory
First App Load
2.81 s203‑211 MB
Subsequent App Load
219 ms17‑249 MB
Inference
9.39 ms0‑231 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