Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
NAFNet-DeNoise

Profile Job Results

Jobs
j576lx19g
Results Ready
Name
nafnet_denoise
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.7
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 256, 256, 3]
Completion Time
5/30/2026, 6:25:35 PM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 1.7-ver.1.1
  • AI Hub: aihub-2026.05.27.0
Estimated Inference Time
46.1 ms
Estimated Peak Memory Usage
1 ‑ 232 MB
Compute Units
NPU
1331
StageTimeMemory
First App Load
33.8 s810‑811 MB
Subsequent App Load
357 ms229‑230 MB
Inference
46.1 ms1‑232 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInference
htp_options.useConvHmxtrue

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

Run on device