Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp31mj9mg
Results Ready
Name
vit
Target Device
  • QCS6490 (Proxy)
  • Android 12
  • Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]
Completion Time
7/19/2025, 3:29:37 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.34.2.250528164111_119506
  • QNN TfLite Delegate: v2.34.2.250528164111_119506
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2025.07.12.0
Estimated Inference Time
80.9 ms
Estimated Peak Memory Usage
2 ‑ 43 MB
Compute Units
NPU
1381
CPU
240
GPU
10
StageTimeMemory
First App Load
6.67 s322‑333 MB
Subsequent App Load
4.54 s279‑355 MB
Inference
80.9 ms2‑43 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
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