Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Yolo-NAS-Quantized

Profile Job Results

Jobs
jgn0nmkv5
Results Ready
Name
yolonas_quantized
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
3/11/2025, 8:02:25 PM
Versions
  • QAIRT: v2.32.0.250228225014_116386
  • QNN Backend API: 5.32.0
  • QNN Core API: 2.24.0
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2025.03.06.0
Estimated Inference Time
15.1 ms
Estimated Peak Memory Usage
1 ‑ 15 MB
Compute Units
NPU
289
StageTimeMemory
First App Load
170 ms0‑7 MB
Subsequent App Load
154 ms0‑14 MB
Inference
15.1 ms1‑15 MB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.precisionFLOAT16

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

Run on device