Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Stable-Diffusion-v1.5

Profile Job Results

Jobs
j5w2e9y35
Results Ready
Name
stable_diffusion_v1_5_w8a16_quantized_VaeDecoderQuantizable
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
latent: uint16[1, 64, 64, 4]
Completion Time
4/8/2025, 9:50:40 AM
Versions
  • QAIRT: v2.32.0.250228225014_116386
  • QNN Backend API: 5.32.0
  • QNN Core API: 2.24.0
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2025.03.24.0
Estimated Inference Time
4.69 min
Estimated Peak Memory Usage
312 ‑ 2,607 GB
Compute Units
NPU
189
StageTimeMemory
First App Load
8.66 min620‑1,726 GB
Subsequent App Load
5.97 min552‑1,781 GB
Inference
4.69 min312‑2,607 GB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.precisionFLOAT16

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

Run on device