iPad mini (7th generation)
Geekbench AI Score
4760
Single Precision Score
5211
Half Precision Score
5149
Quantized Score
Geekbench AI 1.7.0 for iOS AArch64
Result Information
| User | M91 |
| Upload Date | February 21 2026 08:15 AM |
| Views | 12 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 26.4 |
| 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% |
1467
272.8 IPS |
|
|
Image Classification (HP)
|
100% |
1540
286.4 IPS |
|
|
Image Classification (Q)
|
96% |
1438
268.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
3573
57.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
3766
61.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
3690
59.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
12079
14.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
13584
15.9 IPS |
|
|
Pose Estimation (Q)
|
96% |
13383
15.7 IPS |
|
|
Object Detection (SP)
|
100% |
1689
133.9 IPS |
|
|
Object Detection (HP)
|
100% |
1371
108.7 IPS |
|
|
Object Detection (Q)
|
91% |
1662
132.8 IPS |
|
|
Face Detection (SP)
|
100% |
6101
72.5 IPS |
|
|
Face Detection (HP)
|
100% |
7303
86.8 IPS |
|
|
Face Detection (Q)
|
100% |
8304
98.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
10116
77.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
11026
85.0 IPS |
|
|
Depth Estimation (Q)
|
85% |
10361
81.1 IPS |
|
|
Style Transfer (SP)
|
100% |
26122
33.6 IPS |
|
|
Style Transfer (HP)
|
100% |
29867
38.4 IPS |
|
|
Style Transfer (Q)
|
96% |
29813
38.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4957
183.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4097
151.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3690
136.3 IPS |
|
|
Text Classification (SP)
|
100% |
5715
7.63 KIPS |
|
|
Text Classification (HP)
|
100% |
9903
13.2 KIPS |
|
|
Text Classification (Q)
|
92% |
9265
12.4 KIPS |
|
|
Machine Translation (SP)
|
100% |
1225
21.1 IPS |
|
|
Machine Translation (HP)
|
100% |
1402
24.1 IPS |
|
|
Machine Translation (Q)
|
98% |
1268
21.9 IPS |
