iPad Pro 13-inch (M4)
Geekbench AI Score
8663
Single Precision Score
10580
Half Precision Score
9313
Quantized Score
Geekbench AI 1.2.0 for iOS AArch64
Result Information
| User | stevetsuida |
| Upload Date | January 29 2025 08:49 PM |
| Views | 16 |
System Information
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M4 |
| System Information | |
|---|---|
| Operating System | iOS 18.3 |
| Model | iPad Pro 13-inch (M4) |
| Model ID | iPad16,5 |
| Motherboard | J720AP |
| CPU Information | |
|---|---|
| Name | Apple M4 |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM |
| Base Frequency | 4.41 GHz |
| Cluster 1 | 3 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 7.21 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
4434
824.5 IPS |
|
|
Image Classification (HP)
|
100% |
4833
898.7 IPS |
|
|
Image Classification (Q)
|
97% |
4123
769.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
4934
80.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
6732
109.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
7160
116.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
27967
32.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
30048
35.1 IPS |
|
|
Pose Estimation (Q)
|
95% |
28574
33.5 IPS |
|
|
Object Detection (SP)
|
100% |
4755
377.2 IPS |
|
|
Object Detection (HP)
|
100% |
5190
411.7 IPS |
|
|
Object Detection (Q)
|
91% |
4432
354.2 IPS |
|
|
Face Detection (SP)
|
100% |
12868
152.9 IPS |
|
|
Face Detection (HP)
|
100% |
16453
195.5 IPS |
|
|
Face Detection (Q)
|
100% |
12007
142.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
20289
156.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
22357
172.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
19310
150.9 IPS |
|
|
Style Transfer (SP)
|
100% |
56938
73.2 IPS |
|
|
Style Transfer (HP)
|
100% |
67086
86.2 IPS |
|
|
Style Transfer (Q)
|
96% |
62920
81.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
11568
427.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
12602
465.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
10270
379.2 IPS |
|
|
Text Classification (SP)
|
100% |
2965
3.96 KIPS |
|
|
Text Classification (HP)
|
100% |
5517
7.36 KIPS |
|
|
Text Classification (Q)
|
93% |
5360
7.19 KIPS |
|
|
Machine Translation (SP)
|
100% |
1606
27.7 IPS |
|
|
Machine Translation (HP)
|
100% |
2019
34.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1635
28.2 IPS |
