Upload Date | September 14 2025 11:05 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
Model | iPhone 16 Pro Max |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2070
385.0 IPS |
|
Image Classification (HP)
|
100% |
15519
2.89 KIPS |
|
Image Classification (Q)
|
97% |
20103
3.75 KIPS |
|
Image Segmentation (SP)
|
100% |
1942
31.5 IPS |
|
Image Segmentation (HP)
|
100% |
18238
295.6 IPS |
|
Image Segmentation (Q)
|
99% |
24121
391.0 IPS |
|
Pose Estimation (SP)
|
100% |
9260
10.8 IPS |
|
Pose Estimation (HP)
|
100% |
153370
179.0 IPS |
|
Pose Estimation (Q)
|
95% |
291336
341.5 IPS |
|
Object Detection (SP)
|
100% |
2340
185.6 IPS |
|
Object Detection (HP)
|
100% |
16367
1.30 KIPS |
|
Object Detection (Q)
|
91% |
22586
1.80 KIPS |
|
Face Detection (SP)
|
100% |
3885
46.2 IPS |
|
Face Detection (HP)
|
100% |
41179
489.3 IPS |
|
Face Detection (Q)
|
100% |
56915
676.3 IPS |
|
Depth Estimation (SP)
|
100% |
8315
64.1 IPS |
|
Depth Estimation (HP)
|
99% |
95601
736.5 IPS |
|
Depth Estimation (Q)
|
85% |
159960
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
20781
26.7 IPS |
|
Style Transfer (HP)
|
100% |
246013
316.3 IPS |
|
Style Transfer (Q)
|
96% |
302698
390.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5573
205.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
50190
1.85 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86946
3.21 KIPS |
|
Text Classification (SP)
|
100% |
3389
4.52 KIPS |
|
Text Classification (HP)
|
100% |
4910
6.55 KIPS |
|
Text Classification (Q)
|
93% |
4866
6.53 KIPS |
|
Machine Translation (SP)
|
100% |
4127
71.1 IPS |
|
Machine Translation (HP)
|
100% |
10314
177.7 IPS |
|
Machine Translation (Q)
|
98% |
11616
200.7 IPS |