Upload Date | November 16 2024 02:20 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,6 |
Model ID | Mac16,6 |
Motherboard | Mac16,6 |
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 | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2118
393.8 IPS |
|
Image Classification (HP)
|
100% |
18001
3.35 KIPS |
|
Image Classification (Q)
|
97% |
23037
4.30 KIPS |
|
Image Segmentation (SP)
|
100% |
2557
41.4 IPS |
|
Image Segmentation (HP)
|
100% |
22680
367.7 IPS |
|
Image Segmentation (Q)
|
99% |
31406
509.1 IPS |
|
Pose Estimation (SP)
|
100% |
19182
22.4 IPS |
|
Pose Estimation (HP)
|
100% |
122794
143.3 IPS |
|
Pose Estimation (Q)
|
95% |
229089
268.5 IPS |
|
Object Detection (SP)
|
100% |
2580
204.7 IPS |
|
Object Detection (HP)
|
100% |
21217
1.68 KIPS |
|
Object Detection (Q)
|
91% |
24257
1.94 KIPS |
|
Face Detection (SP)
|
100% |
4827
57.4 IPS |
|
Face Detection (HP)
|
100% |
39008
463.5 IPS |
|
Face Detection (Q)
|
100% |
64010
760.6 IPS |
|
Depth Estimation (SP)
|
100% |
9104
70.1 IPS |
|
Depth Estimation (HP)
|
99% |
106191
818.1 IPS |
|
Depth Estimation (Q)
|
85% |
177536
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
37100
47.7 IPS |
|
Style Transfer (HP)
|
100% |
230830
296.7 IPS |
|
Style Transfer (Q)
|
96% |
295583
381.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
7244
267.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
46101
1.70 KIPS |
|
Image Super-Resolution (Q)
|
99% |
81623
3.01 KIPS |
|
Text Classification (SP)
|
100% |
2966
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5882
7.85 KIPS |
|
Text Classification (Q)
|
93% |
5517
7.40 KIPS |
|
Machine Translation (SP)
|
100% |
6145
105.8 IPS |
|
Machine Translation (HP)
|
100% |
16200
279.1 IPS |
|
Machine Translation (Q)
|
98% |
16198
279.9 IPS |