User | M91 |
Upload Date | April 10 2025 09:49 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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% |
2076
386.1 IPS |
|
Image Classification (HP)
|
100% |
15271
2.84 KIPS |
|
Image Classification (Q)
|
97% |
19701
3.68 KIPS |
|
Image Segmentation (SP)
|
100% |
1972
32.0 IPS |
|
Image Segmentation (HP)
|
100% |
18225
295.4 IPS |
|
Image Segmentation (Q)
|
99% |
24143
391.4 IPS |
|
Pose Estimation (SP)
|
100% |
9443
11.0 IPS |
|
Pose Estimation (HP)
|
100% |
153396
179.0 IPS |
|
Pose Estimation (Q)
|
95% |
293055
343.5 IPS |
|
Object Detection (SP)
|
100% |
2357
186.9 IPS |
|
Object Detection (HP)
|
100% |
16282
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22644
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3889
46.2 IPS |
|
Face Detection (HP)
|
100% |
41189
489.4 IPS |
|
Face Detection (Q)
|
100% |
58233
691.9 IPS |
|
Depth Estimation (SP)
|
100% |
8337
64.2 IPS |
|
Depth Estimation (HP)
|
99% |
95763
737.8 IPS |
|
Depth Estimation (Q)
|
85% |
164221
1.28 KIPS |
|
Style Transfer (SP)
|
100% |
20961
26.9 IPS |
|
Style Transfer (HP)
|
100% |
245694
315.8 IPS |
|
Style Transfer (Q)
|
96% |
304456
392.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5584
206.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
50419
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85280
3.15 KIPS |
|
Text Classification (SP)
|
100% |
3398
4.54 KIPS |
|
Text Classification (HP)
|
100% |
4491
5.99 KIPS |
|
Text Classification (Q)
|
93% |
4408
5.92 KIPS |
|
Machine Translation (SP)
|
100% |
4121
71.0 IPS |
|
Machine Translation (HP)
|
100% |
10296
177.4 IPS |
|
Machine Translation (Q)
|
98% |
11592
200.3 IPS |