User | klopib |
Upload Date | February 25 2025 09:17 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2082) |
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 | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
9257
1.72 KIPS |
|
Image Classification (HP)
|
100% |
9776
1.82 KIPS |
|
Image Classification (Q)
|
97% |
8431
1.57 KIPS |
|
Image Segmentation (SP)
|
100% |
16782
272.0 IPS |
|
Image Segmentation (HP)
|
100% |
18150
294.2 IPS |
|
Image Segmentation (Q)
|
99% |
18746
303.9 IPS |
|
Pose Estimation (SP)
|
100% |
80414
93.8 IPS |
|
Pose Estimation (HP)
|
100% |
82587
96.4 IPS |
|
Pose Estimation (Q)
|
95% |
73550
86.2 IPS |
|
Object Detection (SP)
|
100% |
8767
695.4 IPS |
|
Object Detection (HP)
|
100% |
9428
747.8 IPS |
|
Object Detection (Q)
|
91% |
7944
634.8 IPS |
|
Face Detection (SP)
|
100% |
33426
397.2 IPS |
|
Face Detection (HP)
|
100% |
36696
436.0 IPS |
|
Face Detection (Q)
|
100% |
28512
338.8 IPS |
|
Depth Estimation (SP)
|
100% |
42549
327.8 IPS |
|
Depth Estimation (HP)
|
99% |
44637
343.9 IPS |
|
Depth Estimation (Q)
|
85% |
36553
285.7 IPS |
|
Style Transfer (SP)
|
100% |
187684
241.3 IPS |
|
Style Transfer (HP)
|
100% |
205770
264.5 IPS |
|
Style Transfer (Q)
|
96% |
191370
247.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
26826
990.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
27772
1.03 KIPS |
|
Image Super-Resolution (Q)
|
99% |
22272
822.4 IPS |
|
Text Classification (SP)
|
100% |
2967
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5368
7.16 KIPS |
|
Text Classification (Q)
|
93% |
5353
7.18 KIPS |
|
Machine Translation (SP)
|
100% |
2936
50.6 IPS |
|
Machine Translation (HP)
|
100% |
3152
54.3 IPS |
|
Machine Translation (Q)
|
98% |
2972
51.4 IPS |