iPhone 15 Pro Max
Geekbench AI Score
2635
Single Precision Score
14233
Half Precision Score
15808
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | srkses |
| Upload Date | August 15 2024 07:55 PM |
| Views | 3 |
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% |
1411
262.4 IPS |
|
|
Image Classification (HP)
|
100% |
6068
1.13 KIPS |
|
|
Image Classification (Q)
|
99% |
6789
1.27 KIPS |
|
|
Image Segmentation (SP)
|
100% |
799
13.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
5177
83.9 IPS |
|
|
Image Segmentation (Q)
|
100% |
5188
84.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
7317
8.54 IPS |
|
|
Pose Estimation (HP)
|
100% |
87574
102.2 IPS |
|
|
Pose Estimation (Q)
|
94% |
129601
152.0 IPS |
|
|
Object Detection (SP)
|
100% |
1423
112.9 IPS |
|
|
Object Detection (HP)
|
100% |
8198
650.3 IPS |
|
|
Object Detection (Q)
|
93% |
10075
803.9 IPS |
|
|
Face Detection (SP)
|
100% |
2112
25.1 IPS |
|
|
Face Detection (HP)
|
100% |
11225
133.4 IPS |
|
|
Face Detection (Q)
|
100% |
12676
150.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
4467
34.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
42156
324.8 IPS |
|
|
Depth Estimation (Q)
|
97% |
49539
383.0 IPS |
|
|
Style Transfer (SP)
|
100% |
12186
15.7 IPS |
|
|
Style Transfer (HP)
|
100% |
127971
164.5 IPS |
|
|
Style Transfer (Q)
|
100% |
126216
162.3 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3709
137.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
18529
684.2 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
25524
945.6 IPS |
|
|
Text Classification (SP)
|
100% |
1743
2.33 KIPS |
|
|
Text Classification (HP)
|
71% |
5688
8.18 KIPS |
|
|
Text Classification (Q)
|
69% |
4328
6.34 KIPS |
|
|
Machine Translation (SP)
|
100% |
1852
31.9 IPS |
|
|
Machine Translation (HP)
|
100% |
2371
40.8 IPS |
|
|
Machine Translation (Q)
|
98% |
2421
41.8 IPS |
