iPad mini (6th generation)
Geekbench AI Score
3097
Single Precision Score
18930
Half Precision Score
21200
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| Upload Date | December 25 2024 11:03 PM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPad mini (6th generation) |
| Model ID | iPad14,2 |
| Motherboard | J311AP |
| CPU Information | |
|---|---|
| Name | Apple A15 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.92 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.77 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1293
240.5 IPS |
|
|
Image Classification (HP)
|
100% |
8864
1.65 KIPS |
|
|
Image Classification (Q)
|
96% |
9803
1.83 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1261
20.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
11827
191.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
13420
217.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
5368
6.26 IPS |
|
|
Pose Estimation (HP)
|
100% |
76938
89.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
80723
94.6 IPS |
|
|
Object Detection (SP)
|
100% |
1391
110.4 IPS |
|
|
Object Detection (HP)
|
99% |
10775
857.1 IPS |
|
|
Object Detection (Q)
|
91% |
11340
906.1 IPS |
|
|
Face Detection (SP)
|
100% |
2589
30.8 IPS |
|
|
Face Detection (HP)
|
100% |
21051
250.1 IPS |
|
|
Face Detection (Q)
|
100% |
31175
370.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
5161
39.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
52103
401.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
67826
530.0 IPS |
|
|
Style Transfer (SP)
|
100% |
16562
21.3 IPS |
|
|
Style Transfer (HP)
|
100% |
148009
190.3 IPS |
|
|
Style Transfer (Q)
|
96% |
139800
180.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3785
139.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
27566
1.02 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
29277
1.08 KIPS |
|
|
Text Classification (SP)
|
100% |
2398
3.20 KIPS |
|
|
Text Classification (HP)
|
100% |
2449
3.27 KIPS |
|
|
Text Classification (Q)
|
93% |
2486
3.34 KIPS |
|
|
Machine Translation (SP)
|
100% |
3325
57.3 IPS |
|
|
Machine Translation (HP)
|
100% |
6207
106.9 IPS |
|
|
Machine Translation (Q)
|
98% |
7081
122.4 IPS |
