iPad mini (7th generation)
Geekbench AI Score
4390
Single Precision Score
5047
Half Precision Score
4666
Quantized Score
Geekbench AI 1.6.1 for iOS AArch64
Result Information
| User | M91 |
| Upload Date | January 28 2026 12:00 PM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.3 |
| Model | iPad mini (7th generation) |
| Model ID | iPad16,1 |
| Motherboard | J410AP |
| 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 | 7.72 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1120
208.3 IPS |
|
|
Image Classification (HP)
|
100% |
1447
269.1 IPS |
|
|
Image Classification (Q)
|
96% |
1022
190.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
3632
58.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
3858
62.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
3691
59.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
12112
14.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
13927
16.3 IPS |
|
|
Pose Estimation (Q)
|
96% |
13506
15.8 IPS |
|
|
Object Detection (SP)
|
100% |
1433
113.7 IPS |
|
|
Object Detection (HP)
|
100% |
1619
128.4 IPS |
|
|
Object Detection (Q)
|
91% |
1606
128.3 IPS |
|
|
Face Detection (SP)
|
100% |
7050
83.8 IPS |
|
|
Face Detection (HP)
|
100% |
8757
104.1 IPS |
|
|
Face Detection (Q)
|
100% |
5589
66.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
10413
80.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
10971
84.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
10508
82.2 IPS |
|
|
Style Transfer (SP)
|
100% |
26518
34.1 IPS |
|
|
Style Transfer (HP)
|
100% |
30562
39.3 IPS |
|
|
Style Transfer (Q)
|
96% |
30365
39.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4872
179.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3808
140.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3964
146.4 IPS |
|
|
Text Classification (SP)
|
100% |
3209
4.28 KIPS |
|
|
Text Classification (HP)
|
99% |
5482
7.32 KIPS |
|
|
Text Classification (Q)
|
93% |
5546
7.44 KIPS |
|
|
Machine Translation (SP)
|
100% |
1240
21.4 IPS |
|
|
Machine Translation (HP)
|
100% |
1391
24.0 IPS |
|
|
Machine Translation (Q)
|
98% |
1527
26.4 IPS |
