Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgj2426v5
Results Ready
Name
yolov7_w8a8
Target Device
  • QCS6490 (Proxy)
  • Android 12
  • Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 640, 640, 3]
Completion Time
10/4/2025, 3:18:23 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.38.0.250901140452_125126
  • QNN TfLite Delegate: v2.38.0.250901140452_125126
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2025.09.26.0
Estimated Inference Time
20.7 ms
Estimated Peak Memory Usage
8 ‑ 53 MB
Compute Units
NPU
220
GPU
1
StageTimeMemory
First App Load
2.88 s152‑163 MB
Subsequent App Load
2.90 s143‑266 MB
Inference
20.7 ms8‑53 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

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

Run on device