User | KickBench |
Upload Date | May 24 2025 12:44 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.4.1 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1600
297.5 IPS |
|
Image Classification (HP)
|
100% |
11325
2.11 KIPS |
|
Image Classification (Q)
|
97% |
15774
2.94 KIPS |
|
Image Segmentation (SP)
|
100% |
1525
24.7 IPS |
|
Image Segmentation (HP)
|
100% |
15662
253.9 IPS |
|
Image Segmentation (Q)
|
99% |
20843
337.9 IPS |
|
Pose Estimation (SP)
|
100% |
7435
8.68 IPS |
|
Pose Estimation (HP)
|
100% |
101920
118.9 IPS |
|
Pose Estimation (Q)
|
95% |
201130
235.7 IPS |
|
Object Detection (SP)
|
100% |
1625
128.9 IPS |
|
Object Detection (HP)
|
100% |
13835
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19020
1.52 KIPS |
|
Face Detection (SP)
|
100% |
2774
33.0 IPS |
|
Face Detection (HP)
|
100% |
36002
427.8 IPS |
|
Face Detection (Q)
|
100% |
53540
636.2 IPS |
|
Depth Estimation (SP)
|
100% |
6343
48.9 IPS |
|
Depth Estimation (HP)
|
99% |
79805
614.9 IPS |
|
Depth Estimation (Q)
|
85% |
125385
980.3 IPS |
|
Style Transfer (SP)
|
100% |
20039
25.8 IPS |
|
Style Transfer (HP)
|
100% |
208449
268.0 IPS |
|
Style Transfer (Q)
|
96% |
251431
324.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4687
173.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
35788
1.32 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56597
2.09 KIPS |
|
Text Classification (SP)
|
100% |
3258
4.35 KIPS |
|
Text Classification (HP)
|
100% |
2232
2.98 KIPS |
|
Text Classification (Q)
|
93% |
2073
2.78 KIPS |
|
Machine Translation (SP)
|
100% |
3159
54.4 IPS |
|
Machine Translation (HP)
|
100% |
6708
115.5 IPS |
|
Machine Translation (Q)
|
98% |
7453
128.8 IPS |