iPhone 15 Pro Max
Geekbench AI Score
2727
Single Precision Score
13896
Half Precision Score
15847
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | pu154r |
| Upload Date | August 16 2024 10:16 PM |
| Views | 5 |
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% |
1456
270.8 IPS |
|
|
Image Classification (HP)
|
100% |
6198
1.15 KIPS |
|
|
Image Classification (Q)
|
99% |
6838
1.28 KIPS |
|
|
Image Segmentation (SP)
|
100% |
822
13.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
5219
84.6 IPS |
|
|
Image Segmentation (Q)
|
100% |
5217
84.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
7748
9.04 IPS |
|
|
Pose Estimation (HP)
|
100% |
88092
102.8 IPS |
|
|
Pose Estimation (Q)
|
94% |
136470
160.1 IPS |
|
|
Object Detection (SP)
|
100% |
1472
116.7 IPS |
|
|
Object Detection (HP)
|
100% |
8184
649.2 IPS |
|
|
Object Detection (Q)
|
93% |
10078
804.2 IPS |
|
|
Face Detection (SP)
|
100% |
2168
25.8 IPS |
|
|
Face Detection (HP)
|
100% |
11188
132.9 IPS |
|
|
Face Detection (Q)
|
100% |
12849
152.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
4551
35.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
43445
334.7 IPS |
|
|
Depth Estimation (Q)
|
97% |
49010
379.0 IPS |
|
|
Style Transfer (SP)
|
100% |
12309
15.8 IPS |
|
|
Style Transfer (HP)
|
100% |
128260
164.9 IPS |
|
|
Style Transfer (Q)
|
100% |
128289
164.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3938
145.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
18518
683.8 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
26176
969.8 IPS |
|
|
Text Classification (SP)
|
100% |
1824
2.43 KIPS |
|
|
Text Classification (HP)
|
71% |
3899
5.61 KIPS |
|
|
Text Classification (Q)
|
69% |
3925
5.75 KIPS |
|
|
Machine Translation (SP)
|
100% |
1914
33.0 IPS |
|
|
Machine Translation (HP)
|
100% |
2558
44.1 IPS |
|
|
Machine Translation (Q)
|
98% |
2453
42.4 IPS |
