User | hyperameba |
Upload Date | May 09 2025 05:20 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.51 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2132
396.4 IPS |
|
Image Classification (HP)
|
100% |
17232
3.20 KIPS |
|
Image Classification (Q)
|
97% |
22971
4.29 KIPS |
|
Image Segmentation (SP)
|
100% |
2372
38.5 IPS |
|
Image Segmentation (HP)
|
100% |
22681
367.7 IPS |
|
Image Segmentation (Q)
|
99% |
31593
512.2 IPS |
|
Pose Estimation (SP)
|
100% |
18359
21.4 IPS |
|
Pose Estimation (HP)
|
100% |
122618
143.1 IPS |
|
Pose Estimation (Q)
|
95% |
230006
269.6 IPS |
|
Object Detection (SP)
|
100% |
2636
209.1 IPS |
|
Object Detection (HP)
|
100% |
20106
1.59 KIPS |
|
Object Detection (Q)
|
91% |
23992
1.92 KIPS |
|
Face Detection (SP)
|
100% |
4887
58.1 IPS |
|
Face Detection (HP)
|
100% |
43997
522.8 IPS |
|
Face Detection (Q)
|
100% |
66048
784.8 IPS |
|
Depth Estimation (SP)
|
100% |
8880
68.4 IPS |
|
Depth Estimation (HP)
|
99% |
104264
803.3 IPS |
|
Depth Estimation (Q)
|
85% |
175911
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
26323
33.8 IPS |
|
Style Transfer (HP)
|
100% |
233023
299.6 IPS |
|
Style Transfer (Q)
|
96% |
296941
383.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
6085
224.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
46789
1.73 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76484
2.82 KIPS |
|
Text Classification (SP)
|
100% |
2936
3.92 KIPS |
|
Text Classification (HP)
|
100% |
5461
7.29 KIPS |
|
Text Classification (Q)
|
93% |
5461
7.33 KIPS |
|
Machine Translation (SP)
|
100% |
6233
107.4 IPS |
|
Machine Translation (HP)
|
100% |
16252
280.0 IPS |
|
Machine Translation (Q)
|
98% |
16293
281.6 IPS |