Profile Job Results
Jobs
jpx62yx1p
Results Ready
Name
yolov10_det_w8a8
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
10/4/2025, 4:04:33 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.09.26.0
Estimated Inference Time
50.1 ms
Estimated Peak Memory Usage
2 ‑ 9 MB
Compute Units
NPU
339
GPU
6
CPU
3
Stage | Time | Memory |
---|---|---|
First App Load | 1.02 s | 8‑10 MB |
Subsequent App Load | 699 ms | 7‑10 MB |
Inference | 50.1 ms | 2‑9 MB |
TensorFlow Lite | Value |
---|---|
number_of_threads | 4 |
NNAPI Delegate | Value |
---|---|
accelerator_name | "qti-dsp" |
execution_preference | kSustainedSpeed |
allow_fp16 | true |
GPUv2 Delegate | Value |
---|---|
inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
Sign up to run this model on a hosted Qualcomm® device!
Run on device