iPad Air 2
Geekbench ML Score
353
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| User | WB_Mochi0 |
| Upload Date | September 20 2025 03:34 AM |
| Views | 9 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.8.5 |
| Model | iPad Air 2 |
| Model ID | iPad5,4 |
| Motherboard | J82AP |
| CPU Information | |
|---|---|
| Name | Apple A8X |
| Topology | 1 Processor, 3 Cores |
| Identifier | ARM |
| Base Frequency | 1.50 GHz |
| L1 Instruction Cache | 64.0 KB x 1 |
| L1 Data Cache | 64.0 KB x 1 |
| L2 Cache | 2.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 1.94 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
500
53.5 IPS |
|
|
Image Classification (F16)
|
100% |
525
56.2 IPS |
|
|
Image Classification (I8)
|
81% |
100
10.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
892
5.51 IPS |
|
|
Image Segmentation (F16)
|
100% |
1144
7.07 IPS |
|
|
Image Segmentation (I8)
|
89% |
207
1.28 IPS |
|
|
Pose Estimation (F32)
|
100% |
320
1.30 IPS |
|
|
Pose Estimation (F16)
|
100% |
550
2.22 IPS |
|
|
Pose Estimation (I8)
|
80% |
41
0.17 IPS |
|
|
Object Detection (F32)
|
100% |
606
21.3 IPS |
|
|
Object Detection (F16)
|
100% |
772
27.1 IPS |
|
|
Object Detection (I8)
|
52% |
174
6.12 IPS |
|
|
Face Detection (F32)
|
100% |
860
9.88 IPS |
|
|
Face Detection (F16)
|
97% |
1219
14.0 IPS |
|
|
Face Detection (I8)
|
75% |
170
1.95 IPS |
|
|
Text Classification (F32)
|
100% |
327
129.2 IPS |
|
|
Text Classification (F16)
|
98% |
383
151.5 IPS |
|
|
Machine Translation (F32)
|
100% |
192
29.6 IPS |
|
|
Machine Translation (F16)
|
100% |
192
29.6 IPS |
