Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp3e1z8x5
Results Ready
Name
sam2_float_SAM2Decoder
Target Device
  • SA8775P ADP
  • Android 14
  • Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
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
10/25/2025, 5:01:22 PM
Options
--qairt_version latest
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.39.0.250925215840_163802-auto
  • QNN TfLite Delegate: v2.39.0.250925215840_163802-auto
  • Android: 14 (UQ1A.240205.002)
  • Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00011-STD.PROD-1.89321.2
  • AI Hub: aihub-2025.10.21.0
Estimated Inference Time
7.57 ms
Estimated Peak Memory Usage
0 ‑ 47 MB
Compute Units
NPU
806
StageTimeMemory
First App Load
7.92 s177‑187 MB
Subsequent App Load
7.82 s171‑313 MB
Inference
7.57 ms0‑47 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue
htp_options.device_id1

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

Run on device