iPad mini（A17 Pro） iPad16,2
Geekbench AI Score
4070
Single Precision Score
6973
Half Precision Score
5686
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| User | idanbo |
| Upload Date | October 24 2024 09:55 AM |
| Views | 34 |
| Notes | iPad mini（A17 Pro） |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 18.0.1 |
| Model | iPad16,2 |
| Model ID | iPad16,2 |
| Motherboard | J411AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.78 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.73 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1752
325.8 IPS |
|
|
Image Classification (HP)
|
100% |
2908
540.8 IPS |
|
|
Image Classification (Q)
|
96% |
2022
377.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
1677
27.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
2462
39.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
3113
50.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
8235
9.61 IPS |
|
|
Pose Estimation (HP)
|
100% |
16645
19.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
14378
16.9 IPS |
|
|
Object Detection (SP)
|
100% |
1807
143.4 IPS |
|
|
Object Detection (HP)
|
97% |
3375
268.7 IPS |
|
|
Object Detection (Q)
|
94% |
2378
189.5 IPS |
|
|
Face Detection (SP)
|
100% |
3399
40.4 IPS |
|
|
Face Detection (HP)
|
100% |
7029
83.5 IPS |
|
|
Face Detection (Q)
|
100% |
3993
47.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
7172
55.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
13650
105.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
9434
73.8 IPS |
|
|
Style Transfer (SP)
|
100% |
21596
27.8 IPS |
|
|
Style Transfer (HP)
|
100% |
32981
42.4 IPS |
|
|
Style Transfer (Q)
|
96% |
27866
36.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5068
187.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6093
225.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4439
163.9 IPS |
|
|
Text Classification (SP)
|
100% |
3228
4.31 KIPS |
|
|
Text Classification (HP)
|
100% |
5659
7.55 KIPS |
|
|
Text Classification (Q)
|
93% |
5632
7.56 KIPS |
|
|
Machine Translation (SP)
|
100% |
3318
57.2 IPS |
|
|
Machine Translation (HP)
|
98% |
6199
107.1 IPS |
|
|
Machine Translation (Q)
|
98% |
6264
108.2 IPS |
