Upload Date | September 18 2024 07:48 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A335) |
Model | MacBook Pro (16-inch, 2021) |
Model ID | MacBookPro18,2 |
Motherboard | MacBookPro18,2 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1306
242.8 IPS |
|
Image Classification (HP)
|
100% |
6862
1.28 KIPS |
|
Image Classification (Q)
|
96% |
6551
1.22 KIPS |
|
Image Segmentation (SP)
|
100% |
1533
24.8 IPS |
|
Image Segmentation (HP)
|
100% |
6473
104.9 IPS |
|
Image Segmentation (Q)
|
99% |
6758
109.6 IPS |
|
Pose Estimation (SP)
|
100% |
10534
12.3 IPS |
|
Pose Estimation (HP)
|
100% |
70524
82.3 IPS |
|
Pose Estimation (Q)
|
95% |
65844
77.2 IPS |
|
Object Detection (SP)
|
100% |
1514
120.1 IPS |
|
Object Detection (HP)
|
99% |
7965
633.6 IPS |
|
Object Detection (Q)
|
91% |
7498
599.2 IPS |
|
Face Detection (SP)
|
100% |
3202
38.0 IPS |
|
Face Detection (HP)
|
100% |
16162
192.0 IPS |
|
Face Detection (Q)
|
100% |
14611
173.6 IPS |
|
Depth Estimation (SP)
|
100% |
5655
43.6 IPS |
|
Depth Estimation (HP)
|
99% |
51279
395.1 IPS |
|
Depth Estimation (Q)
|
85% |
54473
425.7 IPS |
|
Style Transfer (SP)
|
100% |
21419
27.5 IPS |
|
Style Transfer (HP)
|
100% |
120278
154.6 IPS |
|
Style Transfer (Q)
|
96% |
116903
150.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4194
154.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
25842
954.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
27991
1.03 KIPS |
|
Text Classification (SP)
|
100% |
2293
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3907
5.22 KIPS |
|
Text Classification (Q)
|
93% |
3896
5.23 KIPS |
|
Machine Translation (SP)
|
100% |
3229
55.6 IPS |
|
Machine Translation (HP)
|
100% |
1900
32.7 IPS |
|
Machine Translation (Q)
|
98% |
1896
32.8 IPS |