Profile Job Results
Jobs
jp0r23mnp
Results Ready
Name
zipformer_float_ZipformerJoiner
Target Device
- Snapdragon 8 Elite Gen 5 QRD
- Android 16
- Snapdragon® 8 Elite Gen 5 | SM8850
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
encoder_out: float32[1, 512]decoder_out: float32[1, 512]Completion Time
1/27/2026, 5:10:10 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- QAIRT: v2.37.1.250807093845_124904
- Android: 16 (BQ2A.251016.001-BP2A.250605.031.A3)
- Build ID: Kaanapali.LA.1.0.r1-01040-STD.PROD-1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
226 μs
Estimated Peak Memory Usage
0 ‑ 11 MB
Compute Units
NPU
6
| Stage | Time | Memory |
|---|---|---|
First App Load | 83.6 ms | 6‑14 MB |
Subsequent App Load | 71.6 ms | 0‑8 MB |
Inference | 226 μs | 0‑11 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device