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

Profile Job Results

Jobs
jp2wmeqmp
Results Ready
Name
nafnet_deblur
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.9
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 360, 640, 3]
Completion Time
8/22/2026, 9:45:27 PM
Versions
  • Lite RT: 1.4.5
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 1.9-ver.1.0
  • AI Hub: aihub-2026.08.14.0
Estimated Inference Time
80.7 ms
Estimated Peak Memory Usage
0 ‑ 79 MB
Compute Units
NPU
1480
StageTimeMemory
First App Load
3.09 min882 MB
Subsequent App Load
349 ms81‑83 MB
Inference
80.7 ms0‑79 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue

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

Run on device