User | anthonynelzin |
Upload Date | November 12 2024 10:25 AM |
Views | 3 |
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, 14 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2115
393.4 IPS |
|
Image Classification (HP)
|
100% |
17437
3.24 KIPS |
|
Image Classification (Q)
|
97% |
21959
4.10 KIPS |
|
Image Segmentation (SP)
|
100% |
2514
40.8 IPS |
|
Image Segmentation (HP)
|
100% |
22622
366.7 IPS |
|
Image Segmentation (Q)
|
99% |
31259
506.7 IPS |
|
Pose Estimation (SP)
|
100% |
19023
22.2 IPS |
|
Pose Estimation (HP)
|
100% |
123298
143.9 IPS |
|
Pose Estimation (Q)
|
95% |
229780
269.3 IPS |
|
Object Detection (SP)
|
100% |
2554
202.6 IPS |
|
Object Detection (HP)
|
100% |
19271
1.53 KIPS |
|
Object Detection (Q)
|
91% |
24657
1.97 KIPS |
|
Face Detection (SP)
|
100% |
4731
56.2 IPS |
|
Face Detection (HP)
|
100% |
44436
528.0 IPS |
|
Face Detection (Q)
|
100% |
59989
712.8 IPS |
|
Depth Estimation (SP)
|
100% |
9036
69.6 IPS |
|
Depth Estimation (HP)
|
99% |
104446
804.7 IPS |
|
Depth Estimation (Q)
|
85% |
177320
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
36182
46.5 IPS |
|
Style Transfer (HP)
|
100% |
232915
299.4 IPS |
|
Style Transfer (Q)
|
96% |
290567
375.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7107
262.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
45458
1.68 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77556
2.86 KIPS |
|
Text Classification (SP)
|
100% |
2994
4.00 KIPS |
|
Text Classification (HP)
|
100% |
5014
6.69 KIPS |
|
Text Classification (Q)
|
93% |
5119
6.87 KIPS |
|
Machine Translation (SP)
|
100% |
5990
103.2 IPS |
|
Machine Translation (HP)
|
100% |
16037
276.2 IPS |
|
Machine Translation (Q)
|
98% |
16067
277.7 IPS |