iPad mini (6th generation)
Geekbench AI Score
2302
Single Precision Score
2375
Half Precision Score
2175
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | Auhim |
| Upload Date | August 15 2024 09:32 PM |
| Views | 12 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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% |
730
135.7 IPS |
|
|
Image Classification (HP)
|
100% |
651
121.0 IPS |
|
|
Image Classification (Q)
|
99% |
558
104.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
2104
34.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
2112
34.2 IPS |
|
|
Image Segmentation (Q)
|
100% |
2221
36.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
10615
12.4 IPS |
|
|
Pose Estimation (HP)
|
100% |
11588
13.5 IPS |
|
|
Pose Estimation (Q)
|
96% |
10548
12.4 IPS |
|
|
Object Detection (SP)
|
100% |
1109
88.0 IPS |
|
|
Object Detection (HP)
|
100% |
994
78.9 IPS |
|
|
Object Detection (Q)
|
92% |
763
60.9 IPS |
|
|
Face Detection (SP)
|
100% |
3199
38.0 IPS |
|
|
Face Detection (HP)
|
100% |
3733
44.4 IPS |
|
|
Face Detection (Q)
|
100% |
3350
39.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
7209
55.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
7880
60.7 IPS |
|
|
Depth Estimation (Q)
|
97% |
7073
54.7 IPS |
|
|
Style Transfer (SP)
|
100% |
18286
23.5 IPS |
|
|
Style Transfer (HP)
|
100% |
21989
28.3 IPS |
|
|
Style Transfer (Q)
|
100% |
21327
27.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2790
103.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2548
94.1 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
2585
95.8 IPS |
|
|
Text Classification (SP)
|
100% |
371
495.9 IPS |
|
|
Text Classification (HP)
|
100% |
369
492.9 IPS |
|
|
Text Classification (Q)
|
93% |
224
300.8 IPS |
|
|
Machine Translation (SP)
|
100% |
530
9.12 IPS |
|
|
Machine Translation (HP)
|
100% |
593
10.2 IPS |
|
|
Machine Translation (Q)
|
98% |
812
14.0 IPS |
