iPad (7th generation)
Geekbench AI Score
337
Single Precision Score
308
Half Precision Score
249
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | aguijon |
| Upload Date | August 28 2024 09:05 PM |
| Views | 4 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A10 Fusion |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad (7th generation) |
| Model ID | iPad7,12 |
| Motherboard | J172AP |
| CPU Information | |
|---|---|
| Name | Apple A10 Fusion |
| Topology | 1 Processor, 2 Cores |
| Identifier | ARM |
| Base Frequency | 2.32 GHz |
| Cluster 1 | 2 Cores |
| Memory Information | |
|---|---|
| Size | 2.93 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
197
36.7 IPS |
|
|
Image Classification (HP)
|
100% |
172
32.0 IPS |
|
|
Image Classification (Q)
|
99% |
166
31.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
137
2.21 IPS |
|
|
Image Segmentation (HP)
|
100% |
140
2.27 IPS |
|
|
Image Segmentation (Q)
|
100% |
146
2.36 IPS |
|
|
Pose Estimation (SP)
|
100% |
929
1.08 IPS |
|
|
Pose Estimation (HP)
|
100% |
795
0.93 IPS |
|
|
Pose Estimation (Q)
|
94% |
613
0.72 IPS |
|
|
Object Detection (SP)
|
100% |
172
13.7 IPS |
|
|
Object Detection (HP)
|
100% |
165
13.1 IPS |
|
|
Object Detection (Q)
|
92% |
103
8.19 IPS |
|
|
Face Detection (SP)
|
100% |
387
4.60 IPS |
|
|
Face Detection (HP)
|
100% |
385
4.57 IPS |
|
|
Face Detection (Q)
|
100% |
170
2.02 IPS |
|
|
Depth Estimation (SP)
|
100% |
516
3.98 IPS |
|
|
Depth Estimation (HP)
|
99% |
448
3.45 IPS |
|
|
Depth Estimation (Q)
|
97% |
433
3.35 IPS |
|
|
Style Transfer (SP)
|
100% |
1396
1.79 IPS |
|
|
Style Transfer (HP)
|
100% |
1297
1.67 IPS |
|
|
Style Transfer (Q)
|
100% |
1327
1.71 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
392
14.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
389
14.4 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
216
8.00 IPS |
|
|
Text Classification (SP)
|
100% |
148
197.8 IPS |
|
|
Text Classification (HP)
|
100% |
126
168.4 IPS |
|
|
Text Classification (Q)
|
93% |
129
173.3 IPS |
|
|
Machine Translation (SP)
|
100% |
274
4.71 IPS |
|
|
Machine Translation (HP)
|
100% |
225
3.87 IPS |
|
|
Machine Translation (Q)
|
98% |
225
3.89 IPS |
