User | joebot |
Upload Date | March 08 2025 02:32 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.3.1 |
Model | iPad Pro 11-inch (M4) |
Model ID | iPad16,4 |
Motherboard | J718AP |
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 | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1999
371.7 IPS |
|
Image Classification (HP)
|
100% |
17560
3.27 KIPS |
|
Image Classification (Q)
|
97% |
24889
4.64 KIPS |
|
Image Segmentation (SP)
|
100% |
2120
34.4 IPS |
|
Image Segmentation (HP)
|
100% |
22062
357.6 IPS |
|
Image Segmentation (Q)
|
99% |
30464
493.8 IPS |
|
Pose Estimation (SP)
|
100% |
10107
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
124295
145.0 IPS |
|
Pose Estimation (Q)
|
95% |
233011
273.1 IPS |
|
Object Detection (SP)
|
100% |
2255
178.8 IPS |
|
Object Detection (HP)
|
100% |
18327
1.45 KIPS |
|
Object Detection (Q)
|
91% |
25548
2.04 KIPS |
|
Face Detection (SP)
|
100% |
4003
47.6 IPS |
|
Face Detection (HP)
|
100% |
43407
515.8 IPS |
|
Face Detection (Q)
|
100% |
62837
746.6 IPS |
|
Depth Estimation (SP)
|
100% |
8319
64.1 IPS |
|
Depth Estimation (HP)
|
99% |
98698
760.4 IPS |
|
Depth Estimation (Q)
|
85% |
167347
1.31 KIPS |
|
Style Transfer (SP)
|
100% |
25131
32.3 IPS |
|
Style Transfer (HP)
|
100% |
231064
297.0 IPS |
|
Style Transfer (Q)
|
96% |
297755
384.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5876
217.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
48386
1.79 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83240
3.07 KIPS |
|
Text Classification (SP)
|
100% |
2982
3.98 KIPS |
|
Text Classification (HP)
|
100% |
5864
7.83 KIPS |
|
Text Classification (Q)
|
93% |
5860
7.86 KIPS |
|
Machine Translation (SP)
|
100% |
3954
68.1 IPS |
|
Machine Translation (HP)
|
100% |
16359
281.8 IPS |
|
Machine Translation (Q)
|
98% |
17870
308.8 IPS |