| User | MGGeekBench24 |
| Upload Date | November 06 2024 05:41 PM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPad Pro (11-inch 3rd generation) |
| Model ID | iPad13,6 |
| Motherboard | J518AP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.37 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2063
383.7 IPS |
|
|
Image Classification (HP)
|
100% |
1958
364.2 IPS |
|
|
Image Classification (Q)
|
97% |
1865
348.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
2691
43.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
3624
58.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
3672
59.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
16797
19.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
18319
21.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
17050
20.0 IPS |
|
|
Object Detection (SP)
|
100% |
2731
216.6 IPS |
|
|
Object Detection (HP)
|
100% |
2738
217.2 IPS |
|
|
Object Detection (Q)
|
91% |
2214
176.9 IPS |
|
|
Face Detection (SP)
|
100% |
6805
80.9 IPS |
|
|
Face Detection (HP)
|
100% |
8499
101.0 IPS |
|
|
Face Detection (Q)
|
100% |
5897
70.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
12308
94.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
13729
105.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
11248
87.9 IPS |
|
|
Style Transfer (SP)
|
100% |
28630
36.8 IPS |
|
|
Style Transfer (HP)
|
100% |
35110
45.1 IPS |
|
|
Style Transfer (Q)
|
96% |
32346
41.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6477
239.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7165
264.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5409
199.7 IPS |
|
|
Text Classification (SP)
|
100% |
2294
3.06 KIPS |
|
|
Text Classification (HP)
|
100% |
3864
5.16 KIPS |
|
|
Text Classification (Q)
|
93% |
3865
5.19 KIPS |
|
|
Machine Translation (SP)
|
100% |
854
14.7 IPS |
|
|
Machine Translation (HP)
|
100% |
843
14.5 IPS |
|
|
Machine Translation (Q)
|
98% |
894
15.5 IPS |