iPhone 15 Pro Max
Geekbench AI Score
2650
Single Precision Score
13804
Half Precision Score
15699
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | pakitt |
| Upload Date | August 16 2024 01:20 AM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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 | 7.44 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1398
260.1 IPS |
|
|
Image Classification (HP)
|
100% |
6168
1.15 KIPS |
|
|
Image Classification (Q)
|
99% |
6790
1.27 KIPS |
|
|
Image Segmentation (SP)
|
100% |
780
12.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
5201
84.3 IPS |
|
|
Image Segmentation (Q)
|
100% |
5190
84.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
7220
8.42 IPS |
|
|
Pose Estimation (HP)
|
100% |
87996
102.7 IPS |
|
|
Pose Estimation (Q)
|
94% |
131508
154.3 IPS |
|
|
Object Detection (SP)
|
100% |
1441
114.3 IPS |
|
|
Object Detection (HP)
|
100% |
8197
650.2 IPS |
|
|
Object Detection (Q)
|
93% |
10000
797.9 IPS |
|
|
Face Detection (SP)
|
100% |
2111
25.1 IPS |
|
|
Face Detection (HP)
|
100% |
11131
132.3 IPS |
|
|
Face Detection (Q)
|
100% |
12663
150.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
4496
34.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
42191
325.1 IPS |
|
|
Depth Estimation (Q)
|
97% |
47712
368.9 IPS |
|
|
Style Transfer (SP)
|
100% |
12066
15.5 IPS |
|
|
Style Transfer (HP)
|
100% |
127564
164.0 IPS |
|
|
Style Transfer (Q)
|
100% |
127861
164.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3870
142.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
18261
674.3 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
25797
955.8 IPS |
|
|
Text Classification (SP)
|
100% |
1793
2.39 KIPS |
|
|
Text Classification (HP)
|
71% |
3965
5.70 KIPS |
|
|
Text Classification (Q)
|
69% |
3958
5.80 KIPS |
|
|
Machine Translation (SP)
|
100% |
1897
32.7 IPS |
|
|
Machine Translation (HP)
|
100% |
2504
43.1 IPS |
|
|
Machine Translation (Q)
|
98% |
2488
43.0 IPS |
