User | rismay |
Upload Date | June 18 2025 11:52 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
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% |
2117
393.8 IPS |
|
Image Classification (HP)
|
100% |
17387
3.23 KIPS |
|
Image Classification (Q)
|
97% |
22448
4.19 KIPS |
|
Image Segmentation (SP)
|
100% |
2585
41.9 IPS |
|
Image Segmentation (HP)
|
100% |
22739
368.6 IPS |
|
Image Segmentation (Q)
|
99% |
33041
535.6 IPS |
|
Pose Estimation (SP)
|
100% |
19103
22.3 IPS |
|
Pose Estimation (HP)
|
100% |
123390
144.0 IPS |
|
Pose Estimation (Q)
|
95% |
231827
271.7 IPS |
|
Object Detection (SP)
|
100% |
2533
200.9 IPS |
|
Object Detection (HP)
|
100% |
19788
1.57 KIPS |
|
Object Detection (Q)
|
91% |
25570
2.04 KIPS |
|
Face Detection (SP)
|
100% |
4728
56.2 IPS |
|
Face Detection (HP)
|
100% |
45881
545.2 IPS |
|
Face Detection (Q)
|
100% |
60392
717.6 IPS |
|
Depth Estimation (SP)
|
100% |
8958
69.0 IPS |
|
Depth Estimation (HP)
|
99% |
111154
856.4 IPS |
|
Depth Estimation (Q)
|
85% |
181825
1.42 KIPS |
|
Style Transfer (SP)
|
100% |
36510
46.9 IPS |
|
Style Transfer (HP)
|
100% |
233815
300.6 IPS |
|
Style Transfer (Q)
|
96% |
299523
386.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
7195
265.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
47200
1.74 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79168
2.92 KIPS |
|
Text Classification (SP)
|
100% |
2992
3.99 KIPS |
|
Text Classification (HP)
|
100% |
5670
7.57 KIPS |
|
Text Classification (Q)
|
93% |
6287
8.44 KIPS |
|
Machine Translation (SP)
|
100% |
6139
105.7 IPS |
|
Machine Translation (HP)
|
100% |
17045
293.6 IPS |
|
Machine Translation (Q)
|
98% |
16725
289.0 IPS |