User | anthonynelzin |
Upload Date | November 12 2024 10:17 AM |
Views | 2 |
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 | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2108
392.1 IPS |
|
Image Classification (HP)
|
100% |
17267
3.21 KIPS |
|
Image Classification (Q)
|
97% |
21953
4.10 KIPS |
|
Image Segmentation (SP)
|
100% |
2484
40.3 IPS |
|
Image Segmentation (HP)
|
100% |
22644
367.1 IPS |
|
Image Segmentation (Q)
|
99% |
31222
506.1 IPS |
|
Pose Estimation (SP)
|
100% |
19082
22.3 IPS |
|
Pose Estimation (HP)
|
100% |
123224
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
231069
270.8 IPS |
|
Object Detection (SP)
|
100% |
2558
202.9 IPS |
|
Object Detection (HP)
|
100% |
19462
1.54 KIPS |
|
Object Detection (Q)
|
91% |
23735
1.90 KIPS |
|
Face Detection (SP)
|
100% |
4724
56.1 IPS |
|
Face Detection (HP)
|
100% |
44351
527.0 IPS |
|
Face Detection (Q)
|
100% |
64114
761.8 IPS |
|
Depth Estimation (SP)
|
100% |
9103
70.1 IPS |
|
Depth Estimation (HP)
|
99% |
109680
845.0 IPS |
|
Depth Estimation (Q)
|
85% |
177845
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
35960
46.2 IPS |
|
Style Transfer (HP)
|
100% |
232288
298.6 IPS |
|
Style Transfer (Q)
|
96% |
296035
382.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7131
263.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
45498
1.68 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76925
2.84 KIPS |
|
Text Classification (SP)
|
100% |
2943
3.93 KIPS |
|
Text Classification (HP)
|
100% |
5031
6.71 KIPS |
|
Text Classification (Q)
|
93% |
4991
6.70 KIPS |
|
Machine Translation (SP)
|
100% |
6010
103.5 IPS |
|
Machine Translation (HP)
|
100% |
15918
274.2 IPS |
|
Machine Translation (Q)
|
98% |
16123
278.6 IPS |