Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j5wy66emg
Results Ready
Name
lama_dilated
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: float32[1, 512, 512, 3]
mask: float32[1, 512, 512, 1]
Completion Time
10/3/2026, 12:14:12 PM
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.50.0.260828221209
  • QNN TfLite Delegate: v2.50.0.260828221209
  • Qualcomm Linux: 1.9-ver.1.0
  • AI Hub: aihub-2026.09.25.0
Estimated Inference Time
110 ms
Estimated Peak Memory Usage
3 ‑ 106 MB
Compute Units
NPU
340
StageTimeMemory
First App Load
23.2 s446‑447 MB
Subsequent App Load
320 ms101‑102 MB
Inference
110 ms3‑106 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