User | non |
Upload Date | September 20 2024 10:57 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5046f) |
Model | Mac Studio (2023) |
Model ID | Mac14,14 |
Motherboard | Mac14,14 |
CPU Information | |
---|---|
Name | Apple M2 Ultra |
Topology | 1 Processor, 24 Cores |
Identifier | Apple M2 Ultra |
Base Frequency | 3.46 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1453
270.2 IPS |
|
Image Classification (HP)
|
100% |
12396
2.31 KIPS |
|
Image Classification (Q)
|
99% |
6386
1.19 KIPS |
|
Image Segmentation (SP)
|
100% |
1768
28.7 IPS |
|
Image Segmentation (HP)
|
100% |
9255
150.0 IPS |
|
Image Segmentation (Q)
|
100% |
9267
150.2 IPS |
|
Pose Estimation (SP)
|
100% |
18104
21.1 IPS |
|
Pose Estimation (HP)
|
100% |
101970
119.0 IPS |
|
Pose Estimation (Q)
|
94% |
96692
113.4 IPS |
|
Object Detection (SP)
|
100% |
1836
145.6 IPS |
|
Object Detection (HP)
|
99% |
13969
1.11 KIPS |
|
Object Detection (Q)
|
91% |
16908
1.35 KIPS |
|
Face Detection (SP)
|
100% |
3766
44.7 IPS |
|
Face Detection (HP)
|
100% |
23666
281.2 IPS |
|
Face Detection (Q)
|
100% |
36713
436.2 IPS |
|
Depth Estimation (SP)
|
100% |
6445
49.7 IPS |
|
Depth Estimation (HP)
|
99% |
72043
555.1 IPS |
|
Depth Estimation (Q)
|
97% |
80374
621.5 IPS |
|
Style Transfer (SP)
|
100% |
27607
35.5 IPS |
|
Style Transfer (HP)
|
100% |
155834
200.3 IPS |
|
Style Transfer (Q)
|
100% |
156087
200.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5975
220.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
39492
1.46 KIPS |
|
Image Super-Resolution (Q)
|
98% |
46552
1.72 KIPS |
|
Text Classification (SP)
|
100% |
2237
2.99 KIPS |
|
Text Classification (HP)
|
100% |
3867
5.16 KIPS |
|
Text Classification (Q)
|
93% |
3852
5.17 KIPS |
|
Machine Translation (SP)
|
100% |
4940
85.1 IPS |
|
Machine Translation (HP)
|
100% |
2025
34.9 IPS |
|
Machine Translation (Q)
|
98% |
2019
34.9 IPS |