Upload Date | November 21 2024 07:19 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B2091) |
Model | Mac16,2 |
Model ID | Mac16,2 |
Motherboard | Mac16,2 |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M4 |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2016
374.9 IPS |
|
Image Classification (HP)
|
100% |
17359
3.23 KIPS |
|
Image Classification (Q)
|
97% |
24564
4.58 KIPS |
|
Image Segmentation (SP)
|
100% |
2065
33.5 IPS |
|
Image Segmentation (HP)
|
100% |
21142
342.7 IPS |
|
Image Segmentation (Q)
|
99% |
30312
491.4 IPS |
|
Pose Estimation (SP)
|
100% |
9904
11.6 IPS |
|
Pose Estimation (HP)
|
100% |
123226
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
232753
272.8 IPS |
|
Object Detection (SP)
|
100% |
2280
180.9 IPS |
|
Object Detection (HP)
|
100% |
18524
1.47 KIPS |
|
Object Detection (Q)
|
91% |
25746
2.06 KIPS |
|
Face Detection (SP)
|
100% |
3907
46.4 IPS |
|
Face Detection (HP)
|
100% |
43472
516.5 IPS |
|
Face Detection (Q)
|
100% |
60804
722.5 IPS |
|
Depth Estimation (SP)
|
100% |
8326
64.1 IPS |
|
Depth Estimation (HP)
|
99% |
99194
764.2 IPS |
|
Depth Estimation (Q)
|
85% |
171909
1.34 KIPS |
|
Style Transfer (SP)
|
100% |
25132
32.3 IPS |
|
Style Transfer (HP)
|
100% |
234012
300.8 IPS |
|
Style Transfer (Q)
|
96% |
298098
384.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5893
217.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
49141
1.81 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82746
3.06 KIPS |
|
Text Classification (SP)
|
100% |
2976
3.97 KIPS |
|
Text Classification (HP)
|
100% |
5878
7.85 KIPS |
|
Text Classification (Q)
|
93% |
6049
8.12 KIPS |
|
Machine Translation (SP)
|
100% |
3968
68.4 IPS |
|
Machine Translation (HP)
|
100% |
16398
282.5 IPS |
|
Machine Translation (Q)
|
98% |
18081
312.5 IPS |