User | gbenchgs |
Upload Date | January 30 2025 03:07 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.3 |
Model | iPad Pro 13-inch (M4) |
Model ID | iPad16,6 |
Motherboard | J721AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 15.06 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2007
373.2 IPS |
|
Image Classification (HP)
|
100% |
16854
3.13 KIPS |
|
Image Classification (Q)
|
97% |
23792
4.44 KIPS |
|
Image Segmentation (SP)
|
100% |
2076
33.7 IPS |
|
Image Segmentation (HP)
|
100% |
21840
354.0 IPS |
|
Image Segmentation (Q)
|
99% |
30124
488.3 IPS |
|
Pose Estimation (SP)
|
100% |
10056
11.7 IPS |
|
Pose Estimation (HP)
|
100% |
123092
143.6 IPS |
|
Pose Estimation (Q)
|
95% |
231713
271.6 IPS |
|
Object Detection (SP)
|
100% |
2254
178.8 IPS |
|
Object Detection (HP)
|
100% |
18128
1.44 KIPS |
|
Object Detection (Q)
|
91% |
25388
2.03 KIPS |
|
Face Detection (SP)
|
100% |
3954
47.0 IPS |
|
Face Detection (HP)
|
100% |
41796
496.6 IPS |
|
Face Detection (Q)
|
100% |
62253
739.7 IPS |
|
Depth Estimation (SP)
|
100% |
8288
63.9 IPS |
|
Depth Estimation (HP)
|
99% |
98696
760.4 IPS |
|
Depth Estimation (Q)
|
85% |
167192
1.31 KIPS |
|
Style Transfer (SP)
|
100% |
25164
32.3 IPS |
|
Style Transfer (HP)
|
100% |
234334
301.2 IPS |
|
Style Transfer (Q)
|
96% |
296857
383.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5851
216.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
48521
1.79 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82474
3.05 KIPS |
|
Text Classification (SP)
|
100% |
2933
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5886
7.86 KIPS |
|
Text Classification (Q)
|
93% |
5764
7.74 KIPS |
|
Machine Translation (SP)
|
100% |
3861
66.5 IPS |
|
Machine Translation (HP)
|
100% |
16301
280.8 IPS |
|
Machine Translation (Q)
|
98% |
17675
305.4 IPS |