User | ksnyde |
Upload Date | November 10 2024 10:07 PM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5073e) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,4 |
Motherboard | MacBookPro18,4 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.08 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1200
223.1 IPS |
|
Image Classification (HP)
|
100% |
6318
1.17 KIPS |
|
Image Classification (Q)
|
96% |
6136
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
1423
23.1 IPS |
|
Image Segmentation (HP)
|
100% |
9550
154.8 IPS |
|
Image Segmentation (Q)
|
99% |
9543
154.7 IPS |
|
Pose Estimation (SP)
|
100% |
8565
9.99 IPS |
|
Pose Estimation (HP)
|
100% |
71083
82.9 IPS |
|
Pose Estimation (Q)
|
95% |
48680
57.1 IPS |
|
Object Detection (SP)
|
100% |
1413
112.0 IPS |
|
Object Detection (HP)
|
99% |
7295
580.3 IPS |
|
Object Detection (Q)
|
91% |
6848
547.2 IPS |
|
Face Detection (SP)
|
100% |
3006
35.7 IPS |
|
Face Detection (HP)
|
100% |
14910
177.2 IPS |
|
Face Detection (Q)
|
100% |
14063
167.1 IPS |
|
Depth Estimation (SP)
|
100% |
5375
41.4 IPS |
|
Depth Estimation (HP)
|
99% |
50247
387.1 IPS |
|
Depth Estimation (Q)
|
85% |
51058
399.0 IPS |
|
Style Transfer (SP)
|
100% |
20536
26.4 IPS |
|
Style Transfer (HP)
|
100% |
119238
153.3 IPS |
|
Style Transfer (Q)
|
96% |
114243
147.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3784
139.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
24073
888.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
26937
994.7 IPS |
|
Text Classification (SP)
|
100% |
1928
2.57 KIPS |
|
Text Classification (HP)
|
100% |
3400
4.54 KIPS |
|
Text Classification (Q)
|
93% |
3269
4.39 KIPS |
|
Machine Translation (SP)
|
100% |
2788
48.0 IPS |
|
Machine Translation (HP)
|
100% |
2956
50.9 IPS |
|
Machine Translation (Q)
|
98% |
2908
50.2 IPS |