User | drpace |
Upload Date | December 14 2024 08:18 PM |
Views | 13 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,6 |
Motherboard | Mac16,6 |
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% |
2105
391.4 IPS |
|
Image Classification (HP)
|
100% |
17297
3.22 KIPS |
|
Image Classification (Q)
|
97% |
23275
4.34 KIPS |
|
Image Segmentation (SP)
|
100% |
2539
41.2 IPS |
|
Image Segmentation (HP)
|
100% |
22627
366.8 IPS |
|
Image Segmentation (Q)
|
99% |
31528
511.1 IPS |
|
Pose Estimation (SP)
|
100% |
19066
22.2 IPS |
|
Pose Estimation (HP)
|
100% |
123230
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
230829
270.5 IPS |
|
Object Detection (SP)
|
100% |
2537
201.2 IPS |
|
Object Detection (HP)
|
100% |
20200
1.60 KIPS |
|
Object Detection (Q)
|
91% |
23430
1.87 KIPS |
|
Face Detection (SP)
|
100% |
4734
56.2 IPS |
|
Face Detection (HP)
|
100% |
44560
529.5 IPS |
|
Face Detection (Q)
|
100% |
64120
761.9 IPS |
|
Depth Estimation (SP)
|
100% |
8868
68.3 IPS |
|
Depth Estimation (HP)
|
99% |
104741
807.0 IPS |
|
Depth Estimation (Q)
|
85% |
178839
1.40 KIPS |
|
Style Transfer (SP)
|
100% |
35669
45.9 IPS |
|
Style Transfer (HP)
|
100% |
232753
299.2 IPS |
|
Style Transfer (Q)
|
96% |
295059
380.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
7118
262.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
45925
1.70 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78143
2.89 KIPS |
|
Text Classification (SP)
|
100% |
2958
3.95 KIPS |
|
Text Classification (HP)
|
100% |
5458
7.29 KIPS |
|
Text Classification (Q)
|
93% |
5592
7.51 KIPS |
|
Machine Translation (SP)
|
100% |
6040
104.0 IPS |
|
Machine Translation (HP)
|
100% |
15938
274.5 IPS |
|
Machine Translation (Q)
|
98% |
16310
281.8 IPS |