iPad mini (6th generation)
Geekbench AI Score
2682
Single Precision Score
4158
Half Precision Score
3421
Quantized Score
Geekbench AI 1.0.0 Corporate for iOS AArch64
Result Information
| Upload Date | August 11 2024 08:44 AM |
| Views | 2 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.5.1 |
| 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 | 3.78 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
957
178.0 IPS |
|
|
Image Classification (HP)
|
100% |
1364
253.7 IPS |
|
|
Image Classification (Q)
|
99% |
1374
256.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
976
15.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
1031
16.7 IPS |
|
|
Image Segmentation (Q)
|
100% |
1041
16.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
5119
5.97 IPS |
|
|
Pose Estimation (HP)
|
100% |
12357
14.4 IPS |
|
|
Pose Estimation (Q)
|
96% |
10484
12.3 IPS |
|
|
Object Detection (SP)
|
100% |
1314
104.3 IPS |
|
|
Object Detection (HP)
|
97% |
1968
156.7 IPS |
|
|
Object Detection (Q)
|
94% |
1495
119.1 IPS |
|
|
Face Detection (SP)
|
100% |
2157
25.6 IPS |
|
|
Face Detection (HP)
|
100% |
3654
43.4 IPS |
|
|
Face Detection (Q)
|
100% |
2363
28.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
4565
35.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
7512
58.0 IPS |
|
|
Depth Estimation (Q)
|
96% |
3430
26.5 IPS |
|
|
Style Transfer (SP)
|
100% |
15057
19.4 IPS |
|
|
Style Transfer (HP)
|
100% |
23372
30.0 IPS |
|
|
Style Transfer (Q)
|
100% |
23702
30.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3282
121.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4512
166.6 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
3300
122.2 IPS |
|
|
Text Classification (SP)
|
100% |
2363
3.15 KIPS |
|
|
Text Classification (HP)
|
100% |
3845
5.13 KIPS |
|
|
Text Classification (Q)
|
93% |
3826
5.13 KIPS |
|
|
Machine Translation (SP)
|
100% |
2666
45.9 IPS |
|
|
Machine Translation (HP)
|
98% |
4061
70.2 IPS |
|
|
Machine Translation (Q)
|
98% |
4043
69.9 IPS |
