iPad Air (3rd generation)
Geekbench AI Score
521
Single Precision Score
2109
Half Precision Score
767
Quantized Score
Geekbench AI 1.0.0 for iOS AArch64
Result Information
| User | ju83 |
| Upload Date | September 11 2024 04:50 PM |
| Views | 5 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad Air (3rd generation) |
| Model ID | iPad11,3 |
| Motherboard | J217AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.84 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
275
51.1 IPS |
|
|
Image Classification (HP)
|
100% |
2039
379.1 IPS |
|
|
Image Classification (Q)
|
99% |
2034
379.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
251
4.08 IPS |
|
|
Image Segmentation (HP)
|
100% |
394
6.39 IPS |
|
|
Image Segmentation (Q)
|
100% |
394
6.39 IPS |
|
|
Pose Estimation (SP)
|
100% |
1119
1.31 IPS |
|
|
Pose Estimation (HP)
|
100% |
23430
27.3 IPS |
|
|
Pose Estimation (Q)
|
94% |
888
1.04 IPS |
|
|
Object Detection (SP)
|
100% |
292
23.2 IPS |
|
|
Object Detection (HP)
|
100% |
1380
109.5 IPS |
|
|
Object Detection (Q)
|
94% |
203
16.2 IPS |
|
|
Face Detection (SP)
|
100% |
641
7.62 IPS |
|
|
Face Detection (HP)
|
100% |
5258
62.5 IPS |
|
|
Face Detection (Q)
|
100% |
272
3.23 IPS |
|
|
Depth Estimation (SP)
|
100% |
720
5.55 IPS |
|
|
Depth Estimation (HP)
|
99% |
18945
146.0 IPS |
|
|
Depth Estimation (Q)
|
97% |
18856
145.8 IPS |
|
|
Style Transfer (SP)
|
100% |
2079
2.67 IPS |
|
|
Style Transfer (HP)
|
100% |
1948
2.50 IPS |
|
|
Style Transfer (Q)
|
100% |
1948
2.50 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
587
21.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3488
128.8 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
489
18.1 IPS |
|
|
Text Classification (SP)
|
100% |
265
353.9 IPS |
|
|
Text Classification (HP)
|
100% |
304
405.1 IPS |
|
|
Text Classification (Q)
|
93% |
304
407.4 IPS |
|
|
Machine Translation (SP)
|
100% |
438
7.55 IPS |
|
|
Machine Translation (HP)
|
100% |
326
5.62 IPS |
|
|
Machine Translation (Q)
|
98% |
329
5.68 IPS |
