Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp428ml1g
Results Ready
Name
albert_base_v2_hf
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]
attention_masks: float32[1, 384]
mask_indices: int32[1]
Completion Time
11/14/2026, 4:15:07 PM
Options
--qairt_version latest
Versions
  • ONNX Runtime: 1.30.0
  • QNN Execution Provider: 2.5.0
  • QAIRT: v2.51.0.260929181845
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
16.9 ms
Estimated Peak Memory Usage
0 ‑ 35 MB
Compute Units
NPU
326
StageTimeMemory
First App Load
7.48 s464‑465 MB
Subsequent App Load
426 ms32‑242 MB
Inference
16.9 ms0‑35 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"1"
capture_network_visualizationsfalse
context_priority"normal"
offload_graph_io_quantization"1"
num_graph_prepare_threads"1"

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

Run on device