User | f180n4cc1 |
Upload Date | September 20 2025 10:36 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A354) |
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 | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2187
406.7 IPS |
|
Image Classification (HP)
|
100% |
17531
3.26 KIPS |
|
Image Classification (Q)
|
97% |
21870
4.08 KIPS |
|
Image Segmentation (SP)
|
100% |
2459
39.9 IPS |
|
Image Segmentation (HP)
|
100% |
22885
371.0 IPS |
|
Image Segmentation (Q)
|
99% |
31621
512.6 IPS |
|
Pose Estimation (SP)
|
100% |
18251
21.3 IPS |
|
Pose Estimation (HP)
|
100% |
121942
142.3 IPS |
|
Pose Estimation (Q)
|
95% |
228902
268.3 IPS |
|
Object Detection (SP)
|
100% |
2618
207.6 IPS |
|
Object Detection (HP)
|
100% |
19780
1.57 KIPS |
|
Object Detection (Q)
|
91% |
24106
1.93 KIPS |
|
Face Detection (SP)
|
100% |
5166
61.4 IPS |
|
Face Detection (HP)
|
100% |
43729
519.6 IPS |
|
Face Detection (Q)
|
100% |
62642
744.3 IPS |
|
Depth Estimation (SP)
|
100% |
8932
68.8 IPS |
|
Depth Estimation (HP)
|
99% |
102548
790.1 IPS |
|
Depth Estimation (Q)
|
85% |
178411
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
30931
39.8 IPS |
|
Style Transfer (HP)
|
100% |
231170
297.2 IPS |
|
Style Transfer (Q)
|
96% |
316382
408.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
7215
266.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
49067
1.81 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78585
2.90 KIPS |
|
Text Classification (SP)
|
100% |
3275
4.37 KIPS |
|
Text Classification (HP)
|
99% |
5820
7.77 KIPS |
|
Text Classification (Q)
|
93% |
5701
7.65 KIPS |
|
Machine Translation (SP)
|
100% |
6434
110.8 IPS |
|
Machine Translation (HP)
|
100% |
16295
280.7 IPS |
|
Machine Translation (Q)
|
98% |
16444
284.2 IPS |