Upload Date | September 16 2025 07:17 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
Model | Mac16,12 |
Model ID | Mac16,12 |
Motherboard | Mac16,12 |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M4 |
Base Frequency | 2.77 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
879
163.4 IPS |
|
Image Classification (HP)
|
100% |
8973
1.67 KIPS |
|
Image Classification (Q)
|
97% |
19243
3.59 KIPS |
|
Image Segmentation (SP)
|
100% |
706
11.4 IPS |
|
Image Segmentation (HP)
|
100% |
14644
237.4 IPS |
|
Image Segmentation (Q)
|
99% |
20166
326.9 IPS |
|
Pose Estimation (SP)
|
100% |
2813
3.28 IPS |
|
Pose Estimation (HP)
|
100% |
70064
81.8 IPS |
|
Pose Estimation (Q)
|
95% |
123408
144.6 IPS |
|
Object Detection (SP)
|
100% |
1004
79.7 IPS |
|
Object Detection (HP)
|
100% |
10569
838.3 IPS |
|
Object Detection (Q)
|
91% |
13843
1.11 KIPS |
|
Face Detection (SP)
|
100% |
1362
16.2 IPS |
|
Face Detection (HP)
|
100% |
28470
338.3 IPS |
|
Face Detection (Q)
|
100% |
35578
422.7 IPS |
|
Depth Estimation (SP)
|
100% |
3139
24.2 IPS |
|
Depth Estimation (HP)
|
99% |
52865
407.3 IPS |
|
Depth Estimation (Q)
|
85% |
85591
669.2 IPS |
|
Style Transfer (SP)
|
100% |
5433
6.98 IPS |
|
Style Transfer (HP)
|
100% |
135552
174.3 IPS |
|
Style Transfer (Q)
|
96% |
180836
233.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
1755
64.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
28418
1.05 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49031
1.81 KIPS |
|
Text Classification (SP)
|
100% |
910
1.21 KIPS |
|
Text Classification (HP)
|
100% |
4214
5.63 KIPS |
|
Text Classification (Q)
|
93% |
4418
5.93 KIPS |
|
Machine Translation (SP)
|
100% |
1208
20.8 IPS |
|
Machine Translation (HP)
|
100% |
6776
116.7 IPS |
|
Machine Translation (Q)
|
98% |
7462
129.0 IPS |