iPad mini (6th generation)
Geekbench AI Score
2782
Single Precision Score
3000
Half Precision Score
2762
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| User | funskeen |
| Upload Date | December 08 2024 07:40 PM |
| Views | 11 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPad mini (6th generation) |
| Model ID | iPad14,1 |
| Motherboard | J310AP |
| 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% |
674
125.4 IPS |
|
|
Image Classification (HP)
|
100% |
703
130.8 IPS |
|
|
Image Classification (Q)
|
97% |
510
95.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
2051
33.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
2276
36.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
2303
37.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
10886
12.7 IPS |
|
|
Pose Estimation (HP)
|
100% |
11792
13.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
10852
12.7 IPS |
|
|
Object Detection (SP)
|
100% |
1051
83.4 IPS |
|
|
Object Detection (HP)
|
100% |
1027
81.5 IPS |
|
|
Object Detection (Q)
|
91% |
993
79.4 IPS |
|
|
Face Detection (SP)
|
100% |
3847
45.7 IPS |
|
|
Face Detection (HP)
|
100% |
3904
46.4 IPS |
|
|
Face Detection (Q)
|
100% |
3629
43.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
7623
58.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
7261
55.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
6773
52.9 IPS |
|
|
Style Transfer (SP)
|
100% |
18374
23.6 IPS |
|
|
Style Transfer (HP)
|
100% |
22484
28.9 IPS |
|
|
Style Transfer (Q)
|
96% |
20858
26.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3666
135.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2861
105.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2401
88.6 IPS |
|
|
Text Classification (SP)
|
100% |
2462
3.29 KIPS |
|
|
Text Classification (HP)
|
100% |
4241
5.66 KIPS |
|
|
Text Classification (Q)
|
93% |
4214
5.66 KIPS |
|
|
Machine Translation (SP)
|
100% |
362
6.24 IPS |
|
|
Machine Translation (HP)
|
100% |
395
6.81 IPS |
|
|
Machine Translation (Q)
|
98% |
394
6.80 IPS |
