Upload Date | June 23 2025 07:54 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
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 | 2.09 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1090
202.7 IPS |
|
Image Classification (HP)
|
100% |
11419
2.12 KIPS |
|
Image Classification (Q)
|
97% |
16909
3.16 KIPS |
|
Image Segmentation (SP)
|
100% |
1217
19.7 IPS |
|
Image Segmentation (HP)
|
100% |
13350
216.4 IPS |
|
Image Segmentation (Q)
|
99% |
17887
290.0 IPS |
|
Pose Estimation (SP)
|
100% |
5747
6.71 IPS |
|
Pose Estimation (HP)
|
100% |
67685
79.0 IPS |
|
Pose Estimation (Q)
|
95% |
128394
150.5 IPS |
|
Object Detection (SP)
|
100% |
1295
102.7 IPS |
|
Object Detection (HP)
|
100% |
12098
959.6 IPS |
|
Object Detection (Q)
|
91% |
16540
1.32 KIPS |
|
Face Detection (SP)
|
100% |
2199
26.1 IPS |
|
Face Detection (HP)
|
100% |
28156
334.6 IPS |
|
Face Detection (Q)
|
100% |
40704
483.6 IPS |
|
Depth Estimation (SP)
|
100% |
4633
35.7 IPS |
|
Depth Estimation (HP)
|
99% |
61397
473.0 IPS |
|
Depth Estimation (Q)
|
85% |
103924
812.5 IPS |
|
Style Transfer (SP)
|
100% |
11808
15.2 IPS |
|
Style Transfer (HP)
|
100% |
149968
192.8 IPS |
|
Style Transfer (Q)
|
96% |
195173
251.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3409
125.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
32176
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55376
2.04 KIPS |
|
Text Classification (SP)
|
100% |
1755
2.34 KIPS |
|
Text Classification (HP)
|
100% |
3470
4.63 KIPS |
|
Text Classification (Q)
|
93% |
4113
5.52 KIPS |
|
Machine Translation (SP)
|
100% |
2604
44.8 IPS |
|
Machine Translation (HP)
|
100% |
9173
158.0 IPS |
|
Machine Translation (Q)
|
98% |
10359
179.0 IPS |