User | khodaparastan |
Upload Date | April 28 2025 08:34 PM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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 | 3.49 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 96.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6813
1.27 KIPS |
|
Image Classification (HP)
|
100% |
6809
1.27 KIPS |
|
Image Classification (Q)
|
96% |
6437
1.20 KIPS |
|
Image Segmentation (SP)
|
100% |
13926
225.8 IPS |
|
Image Segmentation (HP)
|
100% |
13721
222.4 IPS |
|
Image Segmentation (Q)
|
99% |
12995
210.7 IPS |
|
Pose Estimation (SP)
|
100% |
82174
95.9 IPS |
|
Pose Estimation (HP)
|
100% |
86094
100.5 IPS |
|
Pose Estimation (Q)
|
96% |
83128
97.4 IPS |
|
Object Detection (SP)
|
100% |
6311
500.6 IPS |
|
Object Detection (HP)
|
100% |
6629
525.8 IPS |
|
Object Detection (Q)
|
92% |
6166
492.2 IPS |
|
Face Detection (SP)
|
100% |
27274
324.1 IPS |
|
Face Detection (HP)
|
100% |
28086
333.7 IPS |
|
Face Detection (Q)
|
100% |
24694
293.4 IPS |
|
Depth Estimation (SP)
|
100% |
32897
253.4 IPS |
|
Depth Estimation (HP)
|
99% |
33671
259.4 IPS |
|
Depth Estimation (Q)
|
85% |
30720
240.2 IPS |
|
Style Transfer (SP)
|
100% |
135671
174.4 IPS |
|
Style Transfer (HP)
|
100% |
152690
196.3 IPS |
|
Style Transfer (Q)
|
96% |
149591
193.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
19868
733.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
20482
756.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
17575
649.0 IPS |
|
Text Classification (SP)
|
100% |
2342
3.13 KIPS |
|
Text Classification (HP)
|
100% |
4102
5.47 KIPS |
|
Text Classification (Q)
|
93% |
4148
5.57 KIPS |
|
Machine Translation (SP)
|
100% |
1608
27.7 IPS |
|
Machine Translation (HP)
|
100% |
1690
29.1 IPS |
|
Machine Translation (Q)
|
98% |
1486
25.7 IPS |