Upload Date | November 19 2024 09:31 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,10 |
Model ID | Mac16,10 |
Motherboard | Mac16,10 |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M4 |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1997
371.4 IPS |
|
Image Classification (HP)
|
100% |
18686
3.48 KIPS |
|
Image Classification (Q)
|
97% |
28068
5.24 KIPS |
|
Image Segmentation (SP)
|
100% |
2070
33.6 IPS |
|
Image Segmentation (HP)
|
100% |
21805
353.5 IPS |
|
Image Segmentation (Q)
|
99% |
30354
492.1 IPS |
|
Pose Estimation (SP)
|
100% |
9751
11.4 IPS |
|
Pose Estimation (HP)
|
100% |
123985
144.7 IPS |
|
Pose Estimation (Q)
|
95% |
232196
272.1 IPS |
|
Object Detection (SP)
|
100% |
2288
181.5 IPS |
|
Object Detection (HP)
|
100% |
18873
1.50 KIPS |
|
Object Detection (Q)
|
91% |
26836
2.14 KIPS |
|
Face Detection (SP)
|
100% |
3858
45.8 IPS |
|
Face Detection (HP)
|
100% |
43675
519.0 IPS |
|
Face Detection (Q)
|
100% |
64608
767.7 IPS |
|
Depth Estimation (SP)
|
100% |
8380
64.6 IPS |
|
Depth Estimation (HP)
|
99% |
100337
773.0 IPS |
|
Depth Estimation (Q)
|
85% |
170120
1.33 KIPS |
|
Style Transfer (SP)
|
100% |
25100
32.3 IPS |
|
Style Transfer (HP)
|
100% |
237415
305.2 IPS |
|
Style Transfer (Q)
|
96% |
300949
388.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5696
210.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
50440
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86489
3.19 KIPS |
|
Text Classification (SP)
|
100% |
3404
4.54 KIPS |
|
Text Classification (HP)
|
100% |
6561
8.76 KIPS |
|
Text Classification (Q)
|
93% |
6839
9.18 KIPS |
|
Machine Translation (SP)
|
100% |
3882
66.9 IPS |
|
Machine Translation (HP)
|
100% |
16497
284.2 IPS |
|
Machine Translation (Q)
|
98% |
17064
294.9 IPS |