Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgdm8r3lg
Results Ready
Name
lightglue_lightglue
Target Device
  • Snapdragon 8 Elite Gen 6 QRD
  • Android 17
  • Snapdragon® 8 Elite Gen 6 | SM8950
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
keypoints0: float32[1, 500, 2]
descriptors0: float32[1, 500, 256]
num_keypoints0: int32[1]
keypoints1: float32[1, 500, 2]
descriptors1: float32[1, 500, 256]
num_keypoints1: int32[1]
Completion Time
11/15/2026, 10:20:36 AM
Options
--qairt_version latest
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.51.0.260929181845
  • QNN TfLite Delegate: v2.51.0.260929181845
  • Android: 17 (CQ2A.260820.002-CP2A.260605.016)
  • Build ID: Maili.LA.1.0.r1-00252-STD.PROD-1
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
58.7 ms
Estimated Peak Memory Usage
13 ‑ 688 MB
Compute Units
NPU
1762
CPU
37
StageTimeMemory
First App Load
2.18 min1 GB
Subsequent App Load
512 ms48‑727 MB
Inference
58.7 ms13‑688 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
XNNPACK DelegateValue

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

Run on device