User | sse |
Upload Date | February 19 2025 03:50 PM |
Views | 4 |
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% |
10168
1.89 KIPS |
|
Image Classification (HP)
|
100% |
10077
1.87 KIPS |
|
Image Classification (Q)
|
97% |
8686
1.62 KIPS |
|
Image Segmentation (SP)
|
100% |
19141
310.3 IPS |
|
Image Segmentation (HP)
|
100% |
20145
326.6 IPS |
|
Image Segmentation (Q)
|
99% |
21112
342.2 IPS |
|
Pose Estimation (SP)
|
100% |
108037
126.1 IPS |
|
Pose Estimation (HP)
|
100% |
109425
127.7 IPS |
|
Pose Estimation (Q)
|
95% |
103380
121.2 IPS |
|
Object Detection (SP)
|
100% |
8870
703.6 IPS |
|
Object Detection (HP)
|
100% |
10152
805.2 IPS |
|
Object Detection (Q)
|
91% |
8694
694.7 IPS |
|
Face Detection (SP)
|
100% |
39110
464.7 IPS |
|
Face Detection (HP)
|
100% |
40248
478.2 IPS |
|
Face Detection (Q)
|
100% |
30994
368.3 IPS |
|
Depth Estimation (SP)
|
100% |
44918
346.1 IPS |
|
Depth Estimation (HP)
|
99% |
47591
366.7 IPS |
|
Depth Estimation (Q)
|
85% |
39820
311.2 IPS |
|
Style Transfer (SP)
|
100% |
226806
291.6 IPS |
|
Style Transfer (HP)
|
100% |
239592
308.0 IPS |
|
Style Transfer (Q)
|
96% |
222574
287.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
30127
1.11 KIPS |
|
Image Super-Resolution (HP)
|
100% |
31979
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
25679
948.2 IPS |
|
Text Classification (SP)
|
100% |
2979
3.98 KIPS |
|
Text Classification (HP)
|
100% |
5348
7.14 KIPS |
|
Text Classification (Q)
|
93% |
5353
7.18 KIPS |
|
Machine Translation (SP)
|
100% |
3511
60.5 IPS |
|
Machine Translation (HP)
|
100% |
3564
61.4 IPS |
|
Machine Translation (Q)
|
98% |
3219
55.6 IPS |