iPad Pro (12.9-inch 3rd Generation)
Geekbench ML Score
694
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| User | Pijiuhua |
| Upload Date | July 26 2025 10:43 AM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 26.0 |
| Model | iPad Pro (12.9-inch 3rd Generation) |
| Model ID | iPad8,7 |
| Motherboard | J321AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 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 | 3.66 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
637
68.3 IPS |
|
|
Image Classification (F16)
|
100% |
632
67.7 IPS |
|
|
Image Classification (I8)
|
81% |
217
23.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
932
5.76 IPS |
|
|
Image Segmentation (F16)
|
100% |
935
5.77 IPS |
|
|
Image Segmentation (I8)
|
89% |
1202
7.42 IPS |
|
|
Pose Estimation (F32)
|
100% |
428
1.73 IPS |
|
|
Pose Estimation (F16)
|
100% |
436
1.76 IPS |
|
|
Pose Estimation (I8)
|
80% |
453
1.83 IPS |
|
|
Object Detection (F32)
|
100% |
974
34.2 IPS |
|
|
Object Detection (F16)
|
100% |
982
34.5 IPS |
|
|
Object Detection (I8)
|
52% |
456
16.0 IPS |
|
|
Face Detection (F32)
|
100% |
1123
12.9 IPS |
|
|
Face Detection (F16)
|
100% |
1153
13.2 IPS |
|
|
Face Detection (I8)
|
75% |
732
8.42 IPS |
|
|
Text Classification (F32)
|
100% |
599
236.8 IPS |
|
|
Text Classification (F16)
|
100% |
516
204.0 IPS |
|
|
Machine Translation (F32)
|
100% |
996
153.4 IPS |
|
|
Machine Translation (F16)
|
100% |
995
153.3 IPS |
