iPad mini（A17 Pro） iPad16,2
Geekbench AI Score
3879
Single Precision Score
4343
Half Precision Score
3984
Quantized Score
Geekbench AI 1.1.0 for iOS AArch64
Result Information
| User | idanbo |
| Upload Date | October 24 2024 10:00 AM |
| Views | 46 |
| Notes | iPad mini（A17 Pro） |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| 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% |
1224
227.7 IPS |
|
|
Image Classification (HP)
|
100% |
1328
246.9 IPS |
|
|
Image Classification (Q)
|
97% |
792
147.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
3160
51.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
3424
55.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
3399
55.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
13070
15.3 IPS |
|
|
Pose Estimation (HP)
|
100% |
13495
15.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
12696
14.9 IPS |
|
|
Object Detection (SP)
|
100% |
1452
115.2 IPS |
|
|
Object Detection (HP)
|
100% |
1743
138.3 IPS |
|
|
Object Detection (Q)
|
91% |
1460
116.6 IPS |
|
|
Face Detection (SP)
|
100% |
5433
64.6 IPS |
|
|
Face Detection (HP)
|
100% |
6210
73.8 IPS |
|
|
Face Detection (Q)
|
100% |
5583
66.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
10568
81.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
10936
84.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
8869
69.3 IPS |
|
|
Style Transfer (SP)
|
100% |
27234
35.0 IPS |
|
|
Style Transfer (HP)
|
100% |
30679
39.4 IPS |
|
|
Style Transfer (Q)
|
96% |
28964
37.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4676
172.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3921
144.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3336
123.2 IPS |
|
|
Text Classification (SP)
|
100% |
3223
4.30 KIPS |
|
|
Text Classification (HP)
|
100% |
5635
7.52 KIPS |
|
|
Text Classification (Q)
|
93% |
5628
7.55 KIPS |
|
|
Machine Translation (SP)
|
100% |
447
7.70 IPS |
|
|
Machine Translation (HP)
|
100% |
485
8.36 IPS |
|
|
Machine Translation (Q)
|
98% |
751
13.0 IPS |
