iPad Pro (11-inch, 4th generation)
Geekbench AI Score
3216
Single Precision Score
4752
Half Precision Score
4080
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| User | HdwJunkie |
| Upload Date | September 16 2024 01:43 AM |
| Views | 16 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple M2 |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad Pro (11-inch, 4th generation) |
| Model ID | iPad14,3 |
| Motherboard | J617AP |
| CPU Information | |
|---|---|
| Name | Apple M2 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 15.33 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1511
280.9 IPS |
|
|
Image Classification (HP)
|
100% |
1922
357.4 IPS |
|
|
Image Classification (Q)
|
96% |
1443
269.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
1321
21.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
1304
21.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
1864
30.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
6100
7.12 IPS |
|
|
Pose Estimation (HP)
|
100% |
14389
16.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
12412
14.5 IPS |
|
|
Object Detection (SP)
|
100% |
1592
126.3 IPS |
|
|
Object Detection (HP)
|
97% |
2281
181.6 IPS |
|
|
Object Detection (Q)
|
94% |
1739
138.6 IPS |
|
|
Face Detection (SP)
|
100% |
2872
34.1 IPS |
|
|
Face Detection (HP)
|
100% |
4473
53.1 IPS |
|
|
Face Detection (Q)
|
100% |
2896
34.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
5346
41.2 IPS |
|
|
Depth Estimation (HP)
|
97% |
8605
66.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
6511
50.8 IPS |
|
|
Style Transfer (SP)
|
100% |
17339
22.3 IPS |
|
|
Style Transfer (HP)
|
100% |
27025
34.7 IPS |
|
|
Style Transfer (Q)
|
96% |
22579
29.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3606
133.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4753
175.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3594
132.7 IPS |
|
|
Text Classification (SP)
|
100% |
2251
3.00 KIPS |
|
|
Text Classification (HP)
|
100% |
3180
4.24 KIPS |
|
|
Text Classification (Q)
|
93% |
3157
4.24 KIPS |
|
|
Machine Translation (SP)
|
100% |
2831
48.8 IPS |
|
|
Machine Translation (HP)
|
98% |
4541
78.5 IPS |
|
|
Machine Translation (Q)
|
98% |
4560
78.8 IPS |
