Upload Date | December 28 2024 10:21 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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 | 4.51 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
9981
1.86 KIPS |
|
Image Classification (HP)
|
100% |
10148
1.89 KIPS |
|
Image Classification (Q)
|
97% |
8455
1.58 KIPS |
|
Image Segmentation (SP)
|
100% |
19277
312.5 IPS |
|
Image Segmentation (HP)
|
100% |
20856
338.1 IPS |
|
Image Segmentation (Q)
|
99% |
21166
343.1 IPS |
|
Pose Estimation (SP)
|
100% |
108050
126.1 IPS |
|
Pose Estimation (HP)
|
100% |
109348
127.6 IPS |
|
Pose Estimation (Q)
|
95% |
103650
121.5 IPS |
|
Object Detection (SP)
|
100% |
8994
713.4 IPS |
|
Object Detection (HP)
|
100% |
10026
795.3 IPS |
|
Object Detection (Q)
|
91% |
8566
684.5 IPS |
|
Face Detection (SP)
|
100% |
39070
464.2 IPS |
|
Face Detection (HP)
|
100% |
39697
471.7 IPS |
|
Face Detection (Q)
|
100% |
29809
354.2 IPS |
|
Depth Estimation (SP)
|
100% |
44060
339.5 IPS |
|
Depth Estimation (HP)
|
99% |
46538
358.6 IPS |
|
Depth Estimation (Q)
|
85% |
39638
309.8 IPS |
|
Style Transfer (SP)
|
100% |
222115
285.5 IPS |
|
Style Transfer (HP)
|
100% |
239395
307.7 IPS |
|
Style Transfer (Q)
|
96% |
217271
280.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
29570
1.09 KIPS |
|
Image Super-Resolution (HP)
|
100% |
31558
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
25126
927.8 IPS |
|
Text Classification (SP)
|
100% |
2964
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5410
7.22 KIPS |
|
Text Classification (Q)
|
93% |
5333
7.16 KIPS |
|
Machine Translation (SP)
|
100% |
3498
60.3 IPS |
|
Machine Translation (HP)
|
100% |
3441
59.3 IPS |
|
Machine Translation (Q)
|
98% |
3547
61.3 IPS |