Profile Job Results
Jobs
jgn6o3mq5
Results Ready
Name
ffnet_78s_quantized
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image
: uint8[1, 3, 1024, 2048]Completion Time
11/26/2024, 1:08:50 PM
Versions
- ONNX Runtime: 1.19.2
- QNN: v2.28.2.241116104011_103376
- Android: 15 (AQ3A.240829.003)
- Build ID: Pakala.LA.1.0.r1-01032-STD.PROD-1
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
6.82 ms
Estimated Peak Memory Usage
13 ‑ 84 MB
Compute Units
NPU
301
Stage | Time | Memory |
---|---|---|
First App Load | 3.11 s | 371‑379 MB |
Subsequent App Load | 89.3 ms | 3‑75 MB |
Inference | 6.82 ms | 13‑84 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" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device