User | f180n4cc1 |
Upload Date | January 05 2025 12:31 PM |
Views | 3 |
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 | 4.50 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
9869
1.84 KIPS |
|
Image Classification (HP)
|
100% |
10419
1.94 KIPS |
|
Image Classification (Q)
|
97% |
8628
1.61 KIPS |
|
Image Segmentation (SP)
|
100% |
19447
315.2 IPS |
|
Image Segmentation (HP)
|
100% |
20748
336.3 IPS |
|
Image Segmentation (Q)
|
99% |
21287
345.1 IPS |
|
Pose Estimation (SP)
|
100% |
106636
124.4 IPS |
|
Pose Estimation (HP)
|
100% |
109808
128.1 IPS |
|
Pose Estimation (Q)
|
95% |
103188
120.9 IPS |
|
Object Detection (SP)
|
100% |
8973
711.7 IPS |
|
Object Detection (HP)
|
100% |
10179
807.4 IPS |
|
Object Detection (Q)
|
91% |
8639
690.3 IPS |
|
Face Detection (SP)
|
100% |
38915
462.4 IPS |
|
Face Detection (HP)
|
100% |
37422
444.7 IPS |
|
Face Detection (Q)
|
100% |
29957
356.0 IPS |
|
Depth Estimation (SP)
|
100% |
43935
338.5 IPS |
|
Depth Estimation (HP)
|
99% |
47131
363.1 IPS |
|
Depth Estimation (Q)
|
85% |
39953
312.3 IPS |
|
Style Transfer (SP)
|
100% |
221830
285.2 IPS |
|
Style Transfer (HP)
|
100% |
237531
305.3 IPS |
|
Style Transfer (Q)
|
96% |
220209
284.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
30509
1.13 KIPS |
|
Image Super-Resolution (HP)
|
100% |
31917
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
25555
943.6 IPS |
|
Text Classification (SP)
|
100% |
2979
3.98 KIPS |
|
Text Classification (HP)
|
100% |
5379
7.18 KIPS |
|
Text Classification (Q)
|
93% |
5332
7.16 KIPS |
|
Machine Translation (SP)
|
100% |
3477
59.9 IPS |
|
Machine Translation (HP)
|
100% |
3515
60.5 IPS |
|
Machine Translation (Q)
|
98% |
3496
60.4 IPS |