Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp0xdx29p
Results Ready
Name
overlap_transformer
Target Device
  • Snapdragon 7 Gen 4 QRD
  • Android 15
  • Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
range_image: uint8[1, 1, 64, 900]
Completion Time
11/15/2026, 6:39:16 PM
Options
--qairt_version latest
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.51.0.260929181845
  • QNN TfLite Delegate: v2.51.0.260929181845
  • Android: 15 (AQ3A.250411.001)
  • Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
236 ms
Estimated Peak Memory Usage
7 ‑ 181 MB
Compute Units
NPU
84
CPU
26
GPU
10
StageTimeMemory
First App Load
3.60 s287‑294 MB
Subsequent App Load
254 ms20‑197 MB
Inference
236 ms7‑181 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
GPUv2 DelegateValue
inference_preferenceTFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED
inference_priority1TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY
inference_priority2TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE
inference_priority3TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION
XNNPACK DelegateValue

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

Run on device