Upload Date | April 13 2025 01:04 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.4 (Build 24E248) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2123
394.8 IPS |
|
Image Classification (HP)
|
100% |
17456
3.25 KIPS |
|
Image Classification (Q)
|
97% |
22956
4.28 KIPS |
|
Image Segmentation (SP)
|
100% |
2349
38.1 IPS |
|
Image Segmentation (HP)
|
100% |
22602
366.4 IPS |
|
Image Segmentation (Q)
|
99% |
31784
515.2 IPS |
|
Pose Estimation (SP)
|
100% |
17708
20.7 IPS |
|
Pose Estimation (HP)
|
100% |
122500
142.9 IPS |
|
Pose Estimation (Q)
|
95% |
229348
268.8 IPS |
|
Object Detection (SP)
|
100% |
2584
204.9 IPS |
|
Object Detection (HP)
|
100% |
19227
1.53 KIPS |
|
Object Detection (Q)
|
91% |
23808
1.90 KIPS |
|
Face Detection (SP)
|
100% |
4725
56.1 IPS |
|
Face Detection (HP)
|
100% |
44223
525.5 IPS |
|
Face Detection (Q)
|
100% |
64084
761.5 IPS |
|
Depth Estimation (SP)
|
100% |
8833
68.0 IPS |
|
Depth Estimation (HP)
|
99% |
105202
810.5 IPS |
|
Depth Estimation (Q)
|
85% |
177922
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
26058
33.5 IPS |
|
Style Transfer (HP)
|
100% |
232754
299.2 IPS |
|
Style Transfer (Q)
|
96% |
293421
378.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
6043
223.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
45457
1.68 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77512
2.86 KIPS |
|
Text Classification (SP)
|
100% |
2919
3.90 KIPS |
|
Text Classification (HP)
|
100% |
6396
8.54 KIPS |
|
Text Classification (Q)
|
93% |
5764
7.74 KIPS |
|
Machine Translation (SP)
|
100% |
6006
103.5 IPS |
|
Machine Translation (HP)
|
100% |
16244
279.8 IPS |
|
Machine Translation (Q)
|
98% |
16606
287.0 IPS |