iPad Air (3rd generation)
Geekbench ML Score
1410
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| User | MaxxxDredd |
| Upload Date | September 30 2022 01:39 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.7 |
| Model | iPad Air (3rd generation) |
| Model ID | iPad11,4 |
| Motherboard | J218AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| L1 Instruction Cache | 48.0 KB x 1 |
| L1 Data Cache | 32.0 KB x 1 |
| L2 Cache | 2.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 2.84 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | Core ML |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
3923
420.3 IPS |
|
|
Image Classification (F16)
|
100% |
3905
418.4 IPS |
|
|
Image Classification (I8)
|
81% |
404
43.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
1397
8.63 IPS |
|
|
Image Segmentation (F16)
|
100% |
1396
8.62 IPS |
|
|
Image Segmentation (I8)
|
89% |
748
4.62 IPS |
|
|
Pose Estimation (F32)
|
100% |
7437
30.1 IPS |
|
|
Pose Estimation (F16)
|
100% |
7646
30.9 IPS |
|
|
Pose Estimation (I8)
|
80% |
142
0.57 IPS |
|
|
Object Detection (F32)
|
94% |
3988
140.0 IPS |
|
|
Object Detection (F16)
|
94% |
4078
143.1 IPS |
|
|
Object Detection (I8)
|
52% |
567
19.9 IPS |
|
|
Face Detection (F32)
|
67% |
3871
44.5 IPS |
|
|
Face Detection (F16)
|
67% |
3866
44.4 IPS |
|
|
Face Detection (I8)
|
75% |
551
6.33 IPS |
|
|
Text Classification (F32)
|
100% |
352
139.4 IPS |
|
|
Text Classification (F16)
|
100% |
354
139.9 IPS |
|
|
Machine Translation (F32)
|
100% |
1001
154.2 IPS |
|
|
Machine Translation (F16)
|
100% |
1001
154.2 IPS |
