User | c0de |
Upload Date | September 17 2025 11:56 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A354) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.25 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2091
388.9 IPS |
|
Image Classification (HP)
|
100% |
18075
3.36 KIPS |
|
Image Classification (Q)
|
97% |
21947
4.10 KIPS |
|
Image Segmentation (SP)
|
100% |
2332
37.8 IPS |
|
Image Segmentation (HP)
|
100% |
23741
384.9 IPS |
|
Image Segmentation (Q)
|
99% |
32850
532.5 IPS |
|
Pose Estimation (SP)
|
100% |
17664
20.6 IPS |
|
Pose Estimation (HP)
|
100% |
123717
144.4 IPS |
|
Pose Estimation (Q)
|
95% |
228003
267.2 IPS |
|
Object Detection (SP)
|
100% |
2456
194.8 IPS |
|
Object Detection (HP)
|
100% |
21521
1.71 KIPS |
|
Object Detection (Q)
|
91% |
17854
1.43 KIPS |
|
Face Detection (SP)
|
100% |
4379
52.0 IPS |
|
Face Detection (HP)
|
100% |
44764
531.9 IPS |
|
Face Detection (Q)
|
100% |
63156
750.4 IPS |
|
Depth Estimation (SP)
|
100% |
8447
65.1 IPS |
|
Depth Estimation (HP)
|
99% |
110447
850.9 IPS |
|
Depth Estimation (Q)
|
85% |
182129
1.42 KIPS |
|
Style Transfer (SP)
|
100% |
30318
39.0 IPS |
|
Style Transfer (HP)
|
100% |
230403
296.2 IPS |
|
Style Transfer (Q)
|
96% |
318274
410.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
7072
261.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
48529
1.79 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77136
2.85 KIPS |
|
Text Classification (SP)
|
100% |
3275
4.37 KIPS |
|
Text Classification (HP)
|
99% |
5555
7.42 KIPS |
|
Text Classification (Q)
|
93% |
5527
7.42 KIPS |
|
Machine Translation (SP)
|
100% |
6062
104.4 IPS |
|
Machine Translation (HP)
|
100% |
15965
275.0 IPS |
|
Machine Translation (Q)
|
98% |
16112
278.4 IPS |