Profile Job Results
Jobs
jpyonnq45
Results Ready
Name
zipformer_encoder
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
cached_len_1: int32[4, 1]cached_len_4: int32[4, 1]cached_len_0: int32[2, 1]cached_len_2: int32[3, 1]cached_len_3: int32[2, 1]cached_avg_0: float32[2, 1, 384]cached_avg_1: float32[4, 1, 384]cached_avg_2: float32[3, 1, 384]cached_avg_3: float32[2, 1, 384]cached_avg_4: float32[4, 1, 384]cached_conv1_0: float32[2, 1, 384, 30]cached_conv1_1: float32[4, 1, 384, 30]cached_conv1_2: float32[3, 1, 384, 30]cached_conv1_3: float32[2, 1, 384, 30]cached_conv1_4: float32[4, 1, 384, 30]cached_conv2_0: float32[2, 1, 384, 30]cached_conv2_1: float32[4, 1, 384, 30]cached_conv2_2: float32[3, 1, 384, 30]cached_conv2_3: float32[2, 1, 384, 30]cached_conv2_4: float32[4, 1, 384, 30]cached_key_0: float32[2, 128, 1, 192]cached_key_1: float32[4, 64, 1, 192]cached_key_2: float32[3, 32, 1, 192]cached_key_3: float32[2, 16, 1, 192]cached_key_4: float32[4, 64, 1, 192]cached_val2_0: float32[2, 128, 1, 96]cached_val2_1: float32[4, 64, 1, 96]cached_val2_2: float32[3, 32, 1, 96]cached_val2_3: float32[2, 16, 1, 96]cached_val2_4: float32[4, 64, 1, 96]cached_val_0: float32[2, 128, 1, 96]cached_val_1: float32[4, 64, 1, 96]cached_val_2: float32[3, 32, 1, 96]cached_val_3: float32[2, 16, 1, 96]cached_val_4: float32[4, 64, 1, 96]x: float32[1, 71, 80]Completion Time
9/19/2026, 4:42:14 PM
Options
--max_profiler_iterations 10 --qairt_version latestVersions
- ONNX Runtime: 1.27.1
- QAIRT: v2.50.0.260828221209
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
18.0 ms
Estimated Peak Memory Usage
8 ‑ 14 MB
Compute Units
NPU
2603
| Stage | Time | Memory |
|---|---|---|
First App Load | 371 ms | 88‑89 MB |
Subsequent App Load | 319 ms | 88‑89 MB |
Inference | 18.0 ms | 8‑14 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