User | JNALMUTRAFI |
Upload Date | October 15 2025 11:55 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3645
677.9 IPS |
|
Image Classification (HP)
|
100% |
3670
682.6 IPS |
|
Image Classification (Q)
|
96% |
3397
634.3 IPS |
|
Image Segmentation (SP)
|
100% |
5715
92.7 IPS |
|
Image Segmentation (HP)
|
100% |
5878
95.3 IPS |
|
Image Segmentation (Q)
|
99% |
5607
90.9 IPS |
|
Pose Estimation (SP)
|
100% |
24665
28.8 IPS |
|
Pose Estimation (HP)
|
100% |
26805
31.3 IPS |
|
Pose Estimation (Q)
|
96% |
26051
30.5 IPS |
|
Object Detection (SP)
|
100% |
3641
288.8 IPS |
|
Object Detection (HP)
|
100% |
3711
294.4 IPS |
|
Object Detection (Q)
|
92% |
3383
270.1 IPS |
|
Face Detection (SP)
|
100% |
10328
122.7 IPS |
|
Face Detection (HP)
|
100% |
12011
142.7 IPS |
|
Face Detection (Q)
|
100% |
10033
119.2 IPS |
|
Depth Estimation (SP)
|
100% |
16860
129.9 IPS |
|
Depth Estimation (HP)
|
99% |
18127
139.7 IPS |
|
Depth Estimation (Q)
|
86% |
16462
128.6 IPS |
|
Style Transfer (SP)
|
100% |
42798
55.0 IPS |
|
Style Transfer (HP)
|
100% |
49251
63.3 IPS |
|
Style Transfer (Q)
|
96% |
47723
61.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
9760
360.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
10399
384.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
9000
332.3 IPS |
|
Text Classification (SP)
|
100% |
2199
2.94 KIPS |
|
Text Classification (HP)
|
100% |
3937
5.26 KIPS |
|
Text Classification (Q)
|
93% |
3821
5.13 KIPS |
|
Machine Translation (SP)
|
100% |
1747
30.1 IPS |
|
Machine Translation (HP)
|
100% |
1780
30.7 IPS |
|
Machine Translation (Q)
|
98% |
1488
25.7 IPS |