User | gshaw1967 |
Upload Date | November 18 2024 02:50 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
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 | 3.07 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4265
793.2 IPS |
|
Image Classification (HP)
|
100% |
3967
737.8 IPS |
|
Image Classification (Q)
|
97% |
3703
691.0 IPS |
|
Image Segmentation (SP)
|
100% |
8607
139.5 IPS |
|
Image Segmentation (HP)
|
100% |
8538
138.4 IPS |
|
Image Segmentation (Q)
|
99% |
8588
139.2 IPS |
|
Pose Estimation (SP)
|
100% |
46918
54.7 IPS |
|
Pose Estimation (HP)
|
100% |
49251
57.5 IPS |
|
Pose Estimation (Q)
|
95% |
45508
53.3 IPS |
|
Object Detection (SP)
|
100% |
4420
350.6 IPS |
|
Object Detection (HP)
|
100% |
4744
376.3 IPS |
|
Object Detection (Q)
|
91% |
4062
324.6 IPS |
|
Face Detection (SP)
|
100% |
17705
210.4 IPS |
|
Face Detection (HP)
|
100% |
18091
215.0 IPS |
|
Face Detection (Q)
|
100% |
13374
158.9 IPS |
|
Depth Estimation (SP)
|
100% |
23402
180.3 IPS |
|
Depth Estimation (HP)
|
99% |
24354
187.6 IPS |
|
Depth Estimation (Q)
|
85% |
19971
156.1 IPS |
|
Style Transfer (SP)
|
100% |
78434
100.8 IPS |
|
Style Transfer (HP)
|
100% |
93333
120.0 IPS |
|
Style Transfer (Q)
|
96% |
87649
113.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
15289
564.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
15763
582.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
12284
453.6 IPS |
|
Text Classification (SP)
|
100% |
2104
2.81 KIPS |
|
Text Classification (HP)
|
100% |
3702
4.94 KIPS |
|
Text Classification (Q)
|
93% |
3820
5.13 KIPS |
|
Machine Translation (SP)
|
100% |
1191
20.5 IPS |
|
Machine Translation (HP)
|
100% |
1180
20.3 IPS |
|
Machine Translation (Q)
|
98% |
1298
22.4 IPS |