Upload Date | December 28 2024 10:23 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
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% |
2134
396.9 IPS |
|
Image Classification (HP)
|
100% |
17931
3.33 KIPS |
|
Image Classification (Q)
|
97% |
21872
4.08 KIPS |
|
Image Segmentation (SP)
|
100% |
2569
41.6 IPS |
|
Image Segmentation (HP)
|
100% |
22849
370.4 IPS |
|
Image Segmentation (Q)
|
99% |
31094
504.1 IPS |
|
Pose Estimation (SP)
|
100% |
19182
22.4 IPS |
|
Pose Estimation (HP)
|
100% |
123381
144.0 IPS |
|
Pose Estimation (Q)
|
95% |
229450
268.9 IPS |
|
Object Detection (SP)
|
100% |
2587
205.2 IPS |
|
Object Detection (HP)
|
100% |
19755
1.57 KIPS |
|
Object Detection (Q)
|
91% |
24266
1.94 KIPS |
|
Face Detection (SP)
|
100% |
4778
56.8 IPS |
|
Face Detection (HP)
|
100% |
39807
473.0 IPS |
|
Face Detection (Q)
|
100% |
63852
758.7 IPS |
|
Depth Estimation (SP)
|
100% |
8926
68.8 IPS |
|
Depth Estimation (HP)
|
99% |
105005
809.0 IPS |
|
Depth Estimation (Q)
|
85% |
178380
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
36420
46.8 IPS |
|
Style Transfer (HP)
|
100% |
231048
297.0 IPS |
|
Style Transfer (Q)
|
96% |
298074
384.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
7169
264.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
45324
1.67 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77276
2.85 KIPS |
|
Text Classification (SP)
|
100% |
2957
3.95 KIPS |
|
Text Classification (HP)
|
100% |
5432
7.25 KIPS |
|
Text Classification (Q)
|
93% |
5320
7.14 KIPS |
|
Machine Translation (SP)
|
100% |
5941
102.3 IPS |
|
Machine Translation (HP)
|
100% |
16251
279.9 IPS |
|
Machine Translation (Q)
|
98% |
16857
291.3 IPS |