User | Loplop |
Upload Date | September 12 2025 08:40 PM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
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 | 2.86 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
9145
1.70 KIPS |
|
Image Classification (HP)
|
100% |
9176
1.71 KIPS |
|
Image Classification (Q)
|
96% |
8615
1.61 KIPS |
|
Image Segmentation (SP)
|
100% |
21239
344.3 IPS |
|
Image Segmentation (HP)
|
100% |
22150
359.1 IPS |
|
Image Segmentation (Q)
|
99% |
21000
340.4 IPS |
|
Pose Estimation (SP)
|
100% |
105096
122.6 IPS |
|
Pose Estimation (HP)
|
100% |
106787
124.6 IPS |
|
Pose Estimation (Q)
|
96% |
103673
121.4 IPS |
|
Object Detection (SP)
|
100% |
8607
682.7 IPS |
|
Object Detection (HP)
|
100% |
9391
744.9 IPS |
|
Object Detection (Q)
|
92% |
8861
707.3 IPS |
|
Face Detection (SP)
|
100% |
32683
388.3 IPS |
|
Face Detection (HP)
|
100% |
37268
442.8 IPS |
|
Face Detection (Q)
|
100% |
34280
407.3 IPS |
|
Depth Estimation (SP)
|
100% |
42301
325.9 IPS |
|
Depth Estimation (HP)
|
99% |
45963
354.1 IPS |
|
Depth Estimation (Q)
|
86% |
40896
319.4 IPS |
|
Style Transfer (SP)
|
100% |
217593
279.7 IPS |
|
Style Transfer (HP)
|
100% |
227739
292.8 IPS |
|
Style Transfer (Q)
|
96% |
218521
282.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
28457
1.05 KIPS |
|
Image Super-Resolution (HP)
|
100% |
29100
1.07 KIPS |
|
Image Super-Resolution (Q)
|
99% |
25387
937.4 IPS |
|
Text Classification (SP)
|
100% |
2249
3.00 KIPS |
|
Text Classification (HP)
|
100% |
3975
5.31 KIPS |
|
Text Classification (Q)
|
93% |
3957
5.31 KIPS |
|
Machine Translation (SP)
|
100% |
1894
32.6 IPS |
|
Machine Translation (HP)
|
100% |
2080
35.8 IPS |
|
Machine Translation (Q)
|
98% |
1986
34.3 IPS |