Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpre2l2k5
Results Ready
Name
sam2_w8a8_SAM2Decoder
Target Device
  • Samsung Galaxy S25
  • Android 15
  • Snapdragon® 8 Elite for Galaxy | SM8750-AC
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_embeddings: uint8[1, 64, 64, 256]
high_res_features1: uint8[1, 256, 256, 32]
high_res_features2: uint8[1, 128, 128, 64]
sparse_embedding: uint8[1, 3, 256]
Completion Time
10/25/2025, 4:23:37 PM
Options
--qairt_version latest
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.39.0.250925215840_163802
  • QNN TfLite Delegate: v2.39.0.250925215840_163802
  • Android: 15 (AP3A.240905.015.A2)
  • AI Hub: aihub-2025.10.21.0
Estimated Inference Time
7.91 ms
Estimated Peak Memory Usage
0 ‑ 63 MB
Compute Units
NPU
867
StageTimeMemory
First App Load
1.68 s175‑184 MB
Subsequent App Load
1.71 s128‑280 MB
Inference
7.91 ms0‑63 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue

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

Run on device