Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
ConvNext-Tiny-w8a16-Quantized

Profile Job Results

Jobs
jgjvol68g
Results Ready
Name
convnext_tiny_w8a16_quantized
Target Device
  • QCS6490 (Proxy)
  • Android 12
  • Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 224, 224, 3]
Completion Time
11/26/2024, 3:27:17 PM
Versions
  • QNN: v2.28.2.241116104011_103376
  • QNN Backend API: 5.28.0
  • QNN Core API: 2.21.0
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2024.11.22.0
Estimated Inference Time
13.6 ms
Estimated Peak Memory Usage
1 ‑ 8 MB
Compute Units
NPU
215
StageTimeMemory
First App Load
348 ms1‑8 MB
Subsequent App Load
272 ms1‑9 MB
Inference
13.6 ms1‑8 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