User | anthonynelzin |
Upload Date | March 13 2025 09:37 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D2082) |
Model | Mac16,9 |
Model ID | Mac16,9 |
Motherboard | Mac16,9 |
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% |
2143
398.6 IPS |
|
Image Classification (HP)
|
100% |
16862
3.14 KIPS |
|
Image Classification (Q)
|
97% |
21049
3.93 KIPS |
|
Image Segmentation (SP)
|
100% |
2574
41.7 IPS |
|
Image Segmentation (HP)
|
100% |
22572
365.9 IPS |
|
Image Segmentation (Q)
|
99% |
31119
504.5 IPS |
|
Pose Estimation (SP)
|
100% |
19280
22.5 IPS |
|
Pose Estimation (HP)
|
100% |
123113
143.7 IPS |
|
Pose Estimation (Q)
|
95% |
229091
268.5 IPS |
|
Object Detection (SP)
|
100% |
2599
206.2 IPS |
|
Object Detection (HP)
|
100% |
18914
1.50 KIPS |
|
Object Detection (Q)
|
91% |
24117
1.93 KIPS |
|
Face Detection (SP)
|
100% |
4815
57.2 IPS |
|
Face Detection (HP)
|
100% |
44085
523.8 IPS |
|
Face Detection (Q)
|
100% |
64030
760.8 IPS |
|
Depth Estimation (SP)
|
100% |
9134
70.4 IPS |
|
Depth Estimation (HP)
|
99% |
103610
798.3 IPS |
|
Depth Estimation (Q)
|
85% |
176317
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
36643
47.1 IPS |
|
Style Transfer (HP)
|
100% |
232977
299.5 IPS |
|
Style Transfer (Q)
|
96% |
296757
383.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7253
267.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
44693
1.65 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76147
2.81 KIPS |
|
Text Classification (SP)
|
100% |
2960
3.95 KIPS |
|
Text Classification (HP)
|
100% |
5470
7.30 KIPS |
|
Text Classification (Q)
|
93% |
5100
6.85 KIPS |
|
Machine Translation (SP)
|
100% |
6164
106.2 IPS |
|
Machine Translation (HP)
|
100% |
16014
275.8 IPS |
|
Machine Translation (Q)
|
98% |
15981
276.2 IPS |