Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Segment-Anything-Model-2

Profile Job Results

Jobs
jgj1jemxg
Results Ready
Name
sam2_encoder
Target Device
  • Snapdragon 7 Gen 4 QRD
  • Android 15
  • Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 1024, 1024, 3]
unnorm_coords: uint8[1, 2, 2]
labels: uint8[1, 2]
Completion Time
6/14/2026, 5:01:52 AM
Versions
  • LiteRT: 1.4.4
  • 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
1.13 s
Estimated Peak Memory Usage
78 ‑ 311 MB
Compute Units
CPU
610
GPU
79
StageTimeMemory
First App Load
52.5 s217‑224 MB
Subsequent App Load
201 ms67‑282 MB
Inference
1.13 s78‑311 MB
Lite RTValue
number_of_threads4
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