Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpyyno8rp
Results Ready
Name
convnext_tiny
Target Device
  • Dragonwing RB3 Gen 2 Vision Kit
  • Qualcomm Linux 1.6
  • Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: uint8[1, 224, 224, 3]
Completion Time
11/14/2026, 8:08:16 PM
Options
--qairt_version latest
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.51.0.260929181845
  • QNN TfLite Delegate: v2.51.0.260929181845
  • Qualcomm Linux: 1.6-ver.1.2
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
37.5 ms
Estimated Peak Memory Usage
3 ‑ 57 MB
Compute Units
CPU
220
NPU
164
GPU
10
StageTimeMemory
First App Load
2.50 s224‑225 MB
Subsequent App Load
653 ms52‑53 MB
Inference
37.5 ms3‑57 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
GPUv2 DelegateValue
inference_preferenceTFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED
inference_priority1TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY
inference_priority2TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE
inference_priority3TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION
XNNPACK DelegateValue

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

Run on device