Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
MediaPipe-Hand-Gesture-Recognition

Profile Job Results

Jobs
jpxmw6w1g
Results Ready
Name
mediapipe_hand_gesture_canned_gesture_classifier
Target Device
  • Snapdragon 7 Gen 4 QRD
  • Android 15
  • Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
hand: uint8[1, 64]
mirrored_hand: uint8[1, 64]
Completion Time
6/14/2026, 3:53:57 AM
Options
--onnx_execution_providers qnn
Versions
  • ONNX Runtime: 1.25.0
  • QAIRT: v2.45.0.260326154327
  • Android: 15 (AQ3A.250411.001)
  • Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
  • AI Hub: aihub-2026.06.08.2
Estimated Inference Time
62.0 μs
Estimated Peak Memory Usage
0 ‑ 16 MB
Compute Units
NPU
98
StageTimeMemory
First App Load
346 ms37‑44 MB
Subsequent App Load
303 ms15‑35 MB
Inference
62.0 μs0‑16 MB
ONNX RuntimeValue
execution_modeSEQUENTIAL
intra_op_num_threads0
inter_op_num_threads0
enable_memory_patternfalse
enable_cpu_memory_arenafalse
graph_optimization_levelENABLE_ALL
QNN Execution ProviderValue
htp_performance_mode"burst"
htp_graph_finalization_optimization_mode"3"
enable_htp_fp16_precision"0"
capture_network_visualizationsfalse
context_priority"normal"
offload_graph_io_quantization"1"

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

Run on device