User | Muuhnkin |
Upload Date | December 03 2024 04:40 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5089c) |
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 | 4.50 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2126
395.3 IPS |
|
Image Classification (HP)
|
100% |
17127
3.19 KIPS |
|
Image Classification (Q)
|
97% |
22432
4.19 KIPS |
|
Image Segmentation (SP)
|
100% |
2475
40.1 IPS |
|
Image Segmentation (HP)
|
100% |
22772
369.2 IPS |
|
Image Segmentation (Q)
|
99% |
31256
506.7 IPS |
|
Pose Estimation (SP)
|
100% |
19131
22.3 IPS |
|
Pose Estimation (HP)
|
100% |
123100
143.6 IPS |
|
Pose Estimation (Q)
|
95% |
229198
268.6 IPS |
|
Object Detection (SP)
|
100% |
2579
204.6 IPS |
|
Object Detection (HP)
|
100% |
18550
1.47 KIPS |
|
Object Detection (Q)
|
91% |
22698
1.81 KIPS |
|
Face Detection (SP)
|
100% |
4845
57.6 IPS |
|
Face Detection (HP)
|
100% |
44071
523.7 IPS |
|
Face Detection (Q)
|
100% |
59400
705.8 IPS |
|
Depth Estimation (SP)
|
100% |
9102
70.1 IPS |
|
Depth Estimation (HP)
|
99% |
103664
798.7 IPS |
|
Depth Estimation (Q)
|
85% |
174508
1.36 KIPS |
|
Style Transfer (SP)
|
100% |
36891
47.4 IPS |
|
Style Transfer (HP)
|
100% |
231620
297.8 IPS |
|
Style Transfer (Q)
|
96% |
294390
379.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
7169
264.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
44645
1.65 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76738
2.83 KIPS |
|
Text Classification (SP)
|
100% |
2901
3.87 KIPS |
|
Text Classification (HP)
|
100% |
5012
6.69 KIPS |
|
Text Classification (Q)
|
93% |
4429
5.94 KIPS |
|
Machine Translation (SP)
|
100% |
6096
105.0 IPS |
|
Machine Translation (HP)
|
100% |
15852
273.1 IPS |
|
Machine Translation (Q)
|
98% |
15841
273.7 IPS |