User | M4ssive |
Upload Date | March 29 2025 07:27 AM |
Views | 12 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
Model | MacBook Pro (14-inch, 2024) |
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 | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2128
395.7 IPS |
|
Image Classification (HP)
|
100% |
16721
3.11 KIPS |
|
Image Classification (Q)
|
97% |
21021
3.92 KIPS |
|
Image Segmentation (SP)
|
100% |
2539
41.2 IPS |
|
Image Segmentation (HP)
|
100% |
22515
365.0 IPS |
|
Image Segmentation (Q)
|
99% |
31253
506.6 IPS |
|
Pose Estimation (SP)
|
100% |
19210
22.4 IPS |
|
Pose Estimation (HP)
|
100% |
122998
143.5 IPS |
|
Pose Estimation (Q)
|
95% |
228920
268.3 IPS |
|
Object Detection (SP)
|
100% |
2600
206.2 IPS |
|
Object Detection (HP)
|
100% |
19007
1.51 KIPS |
|
Object Detection (Q)
|
91% |
23113
1.85 KIPS |
|
Face Detection (SP)
|
100% |
4783
56.8 IPS |
|
Face Detection (HP)
|
100% |
44930
533.9 IPS |
|
Face Detection (Q)
|
100% |
66121
785.7 IPS |
|
Depth Estimation (SP)
|
100% |
9070
69.9 IPS |
|
Depth Estimation (HP)
|
99% |
104629
806.1 IPS |
|
Depth Estimation (Q)
|
85% |
178957
1.40 KIPS |
|
Style Transfer (SP)
|
100% |
37022
47.6 IPS |
|
Style Transfer (HP)
|
100% |
233232
299.8 IPS |
|
Style Transfer (Q)
|
96% |
291337
376.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7261
268.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
45361
1.67 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77355
2.86 KIPS |
|
Text Classification (SP)
|
100% |
2960
3.95 KIPS |
|
Text Classification (HP)
|
100% |
5475
7.31 KIPS |
|
Text Classification (Q)
|
93% |
3880
5.21 KIPS |
|
Machine Translation (SP)
|
100% |
6064
104.5 IPS |
|
Machine Translation (HP)
|
100% |
16401
282.5 IPS |
|
Machine Translation (Q)
|
98% |
16262
281.0 IPS |