Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
SwinV2-Base

Profile Job Results

Jobs
j5wy6yrmg
Results Ready
Name
swinv2_base
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_tensor: float32[1, 224, 224, 3]
Completion Time
10/4/2026, 5:23:40 AM
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
31.8 ms
Estimated Peak Memory Usage
0 ‑ 181 MB
Compute Units
NPU
1804
StageTimeMemory
First App Load
38.5 s502‑503 MB
Subsequent App Load
353 ms182‑184 MB
Inference
31.8 ms0‑181 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