User | gkoblavi |
Upload Date | August 28 2025 11:55 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.5 |
Model | iPad Pro 13-inch (M4) |
Model ID | iPad16,6 |
Motherboard | J721AP |
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 |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2098
390.1 IPS |
|
Image Classification (HP)
|
100% |
17189
3.20 KIPS |
|
Image Classification (Q)
|
97% |
24895
4.65 KIPS |
|
Image Segmentation (SP)
|
100% |
2206
35.8 IPS |
|
Image Segmentation (HP)
|
100% |
22120
358.6 IPS |
|
Image Segmentation (Q)
|
99% |
30622
496.4 IPS |
|
Pose Estimation (SP)
|
100% |
10005
11.7 IPS |
|
Pose Estimation (HP)
|
100% |
123329
143.9 IPS |
|
Pose Estimation (Q)
|
95% |
231989
271.9 IPS |
|
Object Detection (SP)
|
100% |
2427
192.5 IPS |
|
Object Detection (HP)
|
100% |
18327
1.45 KIPS |
|
Object Detection (Q)
|
91% |
26809
2.14 KIPS |
|
Face Detection (SP)
|
100% |
4338
51.5 IPS |
|
Face Detection (HP)
|
100% |
42235
501.8 IPS |
|
Face Detection (Q)
|
100% |
63372
753.0 IPS |
|
Depth Estimation (SP)
|
100% |
8606
66.3 IPS |
|
Depth Estimation (HP)
|
99% |
97433
750.7 IPS |
|
Depth Estimation (Q)
|
85% |
159420
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
21909
28.2 IPS |
|
Style Transfer (HP)
|
100% |
231547
297.7 IPS |
|
Style Transfer (Q)
|
96% |
275245
355.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3040
112.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
49390
1.82 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84172
3.11 KIPS |
|
Text Classification (SP)
|
100% |
3431
4.58 KIPS |
|
Text Classification (HP)
|
100% |
7582
10.1 KIPS |
|
Text Classification (Q)
|
93% |
7452
10.0 KIPS |
|
Machine Translation (SP)
|
100% |
4406
75.9 IPS |
|
Machine Translation (HP)
|
100% |
16707
287.8 IPS |
|
Machine Translation (Q)
|
98% |
9998
172.8 IPS |