Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j5weve045
Results Ready
Name
yolov8_det_quantized
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 640, 640, 3]
Completion Time
1/21/2025, 5:08:23 PM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.01.04.0
Estimated Inference Time
49.0 ms
Estimated Peak Memory Usage
3 ‑ 12 MB
Compute Units
NPU
279
GPU
1
StageTimeMemory
First App Load
1.01 s6‑9 MB
Subsequent App Load
509 ms6‑8 MB
Inference
49.0 ms3‑12 MB
TensorFlow LiteValue
number_of_threads4
NNAPI DelegateValue
accelerator_name"qti-dsp"
execution_preferencekSustainedSpeed
allow_fp16true
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