User | motivio |
Upload Date | August 15 2024 05:41 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,8 |
Motherboard | Mac15,8 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 3.75 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1254
233.3 IPS |
|
Image Classification (HP)
|
100% |
7494
1.39 KIPS |
|
Image Classification (Q)
|
99% |
7653
1.43 KIPS |
|
Image Segmentation (SP)
|
100% |
830
13.5 IPS |
|
Image Segmentation (HP)
|
100% |
6478
105.0 IPS |
|
Image Segmentation (Q)
|
100% |
6392
103.6 IPS |
|
Pose Estimation (SP)
|
100% |
15730
18.4 IPS |
|
Pose Estimation (HP)
|
100% |
102933
120.1 IPS |
|
Pose Estimation (Q)
|
94% |
98625
115.7 IPS |
|
Object Detection (SP)
|
100% |
1364
108.2 IPS |
|
Object Detection (HP)
|
100% |
9531
756.0 IPS |
|
Object Detection (Q)
|
93% |
9922
791.7 IPS |
|
Face Detection (SP)
|
100% |
2541
30.2 IPS |
|
Face Detection (HP)
|
100% |
12698
150.9 IPS |
|
Face Detection (Q)
|
100% |
14889
176.9 IPS |
|
Depth Estimation (SP)
|
100% |
4869
37.5 IPS |
|
Depth Estimation (HP)
|
99% |
59194
456.1 IPS |
|
Depth Estimation (Q)
|
97% |
61327
474.2 IPS |
|
Style Transfer (SP)
|
100% |
16296
20.9 IPS |
|
Style Transfer (HP)
|
100% |
148744
191.2 IPS |
|
Style Transfer (Q)
|
100% |
149462
192.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3952
145.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
19256
711.0 IPS |
|
Image Super-Resolution (Q)
|
98% |
23499
870.6 IPS |
|
Text Classification (SP)
|
100% |
751
1.00 KIPS |
|
Text Classification (HP)
|
100% |
4337
5.79 KIPS |
|
Text Classification (Q)
|
93% |
4301
5.77 KIPS |
|
Machine Translation (SP)
|
100% |
2283
39.3 IPS |
|
Machine Translation (HP)
|
100% |
2740
47.2 IPS |
|
Machine Translation (Q)
|
98% |
2732
47.2 IPS |