User | Qetesh |
Upload Date | August 16 2024 09:20 AM |
Views | 17 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,9 |
Motherboard | Mac15,9 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.04 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1496
278.3 IPS |
|
Image Classification (HP)
|
100% |
16071
2.99 KIPS |
|
Image Classification (Q)
|
99% |
16664
3.11 KIPS |
|
Image Segmentation (SP)
|
100% |
1851
30.0 IPS |
|
Image Segmentation (HP)
|
100% |
13804
223.8 IPS |
|
Image Segmentation (Q)
|
100% |
13772
223.3 IPS |
|
Pose Estimation (SP)
|
100% |
16664
19.4 IPS |
|
Pose Estimation (HP)
|
100% |
116965
136.5 IPS |
|
Pose Estimation (Q)
|
94% |
114694
134.5 IPS |
|
Object Detection (SP)
|
100% |
1952
154.8 IPS |
|
Object Detection (HP)
|
100% |
16363
1.30 KIPS |
|
Object Detection (Q)
|
91% |
18769
1.50 KIPS |
|
Face Detection (SP)
|
100% |
4179
49.7 IPS |
|
Face Detection (HP)
|
100% |
24489
291.0 IPS |
|
Face Detection (Q)
|
100% |
36155
429.6 IPS |
|
Depth Estimation (SP)
|
100% |
7383
56.9 IPS |
|
Depth Estimation (HP)
|
99% |
87845
676.8 IPS |
|
Depth Estimation (Q)
|
97% |
90254
697.9 IPS |
|
Style Transfer (SP)
|
100% |
30435
39.1 IPS |
|
Style Transfer (HP)
|
100% |
164057
210.9 IPS |
|
Style Transfer (Q)
|
100% |
166912
214.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5839
215.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
44760
1.65 KIPS |
|
Image Super-Resolution (Q)
|
98% |
53224
1.97 KIPS |
|
Text Classification (SP)
|
100% |
2899
3.87 KIPS |
|
Text Classification (HP)
|
100% |
4821
6.43 KIPS |
|
Text Classification (Q)
|
93% |
4790
6.43 KIPS |
|
Machine Translation (SP)
|
100% |
4762
82.0 IPS |
|
Machine Translation (HP)
|
100% |
2689
46.3 IPS |
|
Machine Translation (Q)
|
98% |
2682
46.4 IPS |