User | dank1 |
Upload Date | August 16 2024 12:21 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
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 | 4.04 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1499
278.7 IPS |
|
Image Classification (HP)
|
100% |
15637
2.91 KIPS |
|
Image Classification (Q)
|
99% |
15975
2.98 KIPS |
|
Image Segmentation (SP)
|
100% |
1887
30.6 IPS |
|
Image Segmentation (HP)
|
100% |
13771
223.2 IPS |
|
Image Segmentation (Q)
|
100% |
13763
223.1 IPS |
|
Pose Estimation (SP)
|
100% |
16821
19.6 IPS |
|
Pose Estimation (HP)
|
100% |
116810
136.3 IPS |
|
Pose Estimation (Q)
|
94% |
113562
133.2 IPS |
|
Object Detection (SP)
|
100% |
1976
156.7 IPS |
|
Object Detection (HP)
|
100% |
15185
1.20 KIPS |
|
Object Detection (Q)
|
91% |
16603
1.33 KIPS |
|
Face Detection (SP)
|
100% |
4047
48.1 IPS |
|
Face Detection (HP)
|
100% |
24558
291.8 IPS |
|
Face Detection (Q)
|
100% |
38509
457.6 IPS |
|
Depth Estimation (SP)
|
100% |
7323
56.4 IPS |
|
Depth Estimation (HP)
|
99% |
83307
641.8 IPS |
|
Depth Estimation (Q)
|
97% |
86431
668.3 IPS |
|
Style Transfer (SP)
|
100% |
30834
39.6 IPS |
|
Style Transfer (HP)
|
100% |
162988
209.5 IPS |
|
Style Transfer (Q)
|
100% |
163743
210.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5774
213.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
37873
1.40 KIPS |
|
Image Super-Resolution (Q)
|
98% |
50143
1.86 KIPS |
|
Text Classification (SP)
|
100% |
2760
3.68 KIPS |
|
Text Classification (HP)
|
100% |
4737
6.32 KIPS |
|
Text Classification (Q)
|
93% |
4631
6.22 KIPS |
|
Machine Translation (SP)
|
100% |
4747
81.8 IPS |
|
Machine Translation (HP)
|
100% |
2675
46.1 IPS |
|
Machine Translation (Q)
|
98% |
2647
45.8 IPS |