User | Toda |
Upload Date | September 08 2025 10:58 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
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 | 3.26 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7005
1.30 KIPS |
|
Image Classification (HP)
|
100% |
7015
1.30 KIPS |
|
Image Classification (Q)
|
96% |
6445
1.20 KIPS |
|
Image Segmentation (SP)
|
100% |
14995
243.1 IPS |
|
Image Segmentation (HP)
|
100% |
14099
228.5 IPS |
|
Image Segmentation (Q)
|
99% |
13296
215.5 IPS |
|
Pose Estimation (SP)
|
100% |
83386
97.3 IPS |
|
Pose Estimation (HP)
|
100% |
89675
104.6 IPS |
|
Pose Estimation (Q)
|
96% |
86655
101.5 IPS |
|
Object Detection (SP)
|
100% |
6643
526.9 IPS |
|
Object Detection (HP)
|
100% |
6825
541.3 IPS |
|
Object Detection (Q)
|
92% |
6316
504.2 IPS |
|
Face Detection (SP)
|
100% |
27570
327.6 IPS |
|
Face Detection (HP)
|
100% |
29094
345.7 IPS |
|
Face Detection (Q)
|
100% |
25136
298.7 IPS |
|
Depth Estimation (SP)
|
100% |
34083
262.6 IPS |
|
Depth Estimation (HP)
|
99% |
35076
270.2 IPS |
|
Depth Estimation (Q)
|
86% |
32109
250.8 IPS |
|
Style Transfer (SP)
|
100% |
136964
176.1 IPS |
|
Style Transfer (HP)
|
100% |
156565
201.3 IPS |
|
Style Transfer (Q)
|
96% |
152641
197.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
20528
758.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
24266
896.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
21363
788.8 IPS |
|
Text Classification (SP)
|
100% |
2362
3.15 KIPS |
|
Text Classification (HP)
|
100% |
3835
5.12 KIPS |
|
Text Classification (Q)
|
93% |
3808
5.11 KIPS |
|
Machine Translation (SP)
|
100% |
3577
61.6 IPS |
|
Machine Translation (HP)
|
100% |
3769
64.9 IPS |
|
Machine Translation (Q)
|
98% |
3629
62.7 IPS |