User | khodaparastan |
Upload Date | May 06 2025 02:27 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 96.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1375
255.6 IPS |
|
Image Classification (HP)
|
100% |
14880
2.77 KIPS |
|
Image Classification (Q)
|
96% |
17423
3.25 KIPS |
|
Image Segmentation (SP)
|
100% |
1639
26.6 IPS |
|
Image Segmentation (HP)
|
100% |
19859
321.9 IPS |
|
Image Segmentation (Q)
|
99% |
24749
401.2 IPS |
|
Pose Estimation (SP)
|
100% |
12823
15.0 IPS |
|
Pose Estimation (HP)
|
100% |
107117
125.0 IPS |
|
Pose Estimation (Q)
|
95% |
105547
123.7 IPS |
|
Object Detection (SP)
|
100% |
1658
131.5 IPS |
|
Object Detection (HP)
|
99% |
16004
1.27 KIPS |
|
Object Detection (Q)
|
91% |
17644
1.41 KIPS |
|
Face Detection (SP)
|
100% |
3434
40.8 IPS |
|
Face Detection (HP)
|
100% |
35269
419.1 IPS |
|
Face Detection (Q)
|
100% |
46383
551.1 IPS |
|
Depth Estimation (SP)
|
100% |
5998
46.2 IPS |
|
Depth Estimation (HP)
|
99% |
88101
678.8 IPS |
|
Depth Estimation (Q)
|
85% |
110764
865.6 IPS |
|
Style Transfer (SP)
|
100% |
25015
32.2 IPS |
|
Style Transfer (HP)
|
100% |
206480
265.4 IPS |
|
Style Transfer (Q)
|
96% |
192392
248.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5139
189.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
42371
1.56 KIPS |
|
Image Super-Resolution (Q)
|
99% |
51145
1.89 KIPS |
|
Text Classification (SP)
|
100% |
2349
3.14 KIPS |
|
Text Classification (HP)
|
100% |
4177
5.58 KIPS |
|
Text Classification (Q)
|
93% |
4163
5.59 KIPS |
|
Machine Translation (SP)
|
100% |
4343
74.8 IPS |
|
Machine Translation (HP)
|
100% |
3911
67.4 IPS |
|
Machine Translation (Q)
|
98% |
4106
71.0 IPS |