Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgj24q4v5
Results Ready
Name
deeplab_xception_w8a8
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 480, 520, 3]
Completion Time
10/5/2025, 7:19:36 AM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.09.26.0
Estimated Inference Time
251 ms
Estimated Peak Memory Usage
8 ‑ 33 MB
Compute Units
NPU
199
GPU
6
CPU
3
StageTimeMemory
First App Load
2.53 s23‑26 MB
Subsequent App Load
3.02 s39‑41 MB
Inference
251 ms8‑33 MB
TensorFlow LiteValue
number_of_threads4
NNAPI DelegateValue
accelerator_name"qti-dsp"
execution_preferencekSustainedSpeed
allow_fp16true
NNAPI DelegateValue
accelerator_name"qti-hta"
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
XNNPACK DelegateValue

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

Run on device