Upload Date | November 06 2024 02:44 PM |
Views | 27 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,3 |
Model ID | Mac16,3 |
Motherboard | Mac16,3 |
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 | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1958
364.1 IPS |
|
Image Classification (HP)
|
100% |
18277
3.40 KIPS |
|
Image Classification (Q)
|
97% |
28951
5.40 KIPS |
|
Image Segmentation (SP)
|
100% |
2094
33.9 IPS |
|
Image Segmentation (HP)
|
100% |
21981
356.3 IPS |
|
Image Segmentation (Q)
|
99% |
30235
490.1 IPS |
|
Pose Estimation (SP)
|
100% |
9840
11.5 IPS |
|
Pose Estimation (HP)
|
100% |
123580
144.2 IPS |
|
Pose Estimation (Q)
|
95% |
232239
272.2 IPS |
|
Object Detection (SP)
|
100% |
2230
176.9 IPS |
|
Object Detection (HP)
|
100% |
18643
1.48 KIPS |
|
Object Detection (Q)
|
91% |
27131
2.17 KIPS |
|
Face Detection (SP)
|
100% |
3722
44.2 IPS |
|
Face Detection (HP)
|
100% |
43377
515.4 IPS |
|
Face Detection (Q)
|
100% |
60724
721.5 IPS |
|
Depth Estimation (SP)
|
100% |
8257
63.6 IPS |
|
Depth Estimation (HP)
|
99% |
99887
769.6 IPS |
|
Depth Estimation (Q)
|
85% |
170022
1.33 KIPS |
|
Style Transfer (SP)
|
100% |
24862
32.0 IPS |
|
Style Transfer (HP)
|
100% |
235041
302.1 IPS |
|
Style Transfer (Q)
|
96% |
297713
384.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5843
215.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
49565
1.83 KIPS |
|
Image Super-Resolution (Q)
|
99% |
90858
3.35 KIPS |
|
Text Classification (SP)
|
100% |
3004
4.01 KIPS |
|
Text Classification (HP)
|
100% |
7018
9.37 KIPS |
|
Text Classification (Q)
|
93% |
8084
10.8 KIPS |
|
Machine Translation (SP)
|
100% |
3732
64.3 IPS |
|
Machine Translation (HP)
|
100% |
17216
296.6 IPS |
|
Machine Translation (Q)
|
98% |
18891
326.5 IPS |