User | j4ys0n |
Upload Date | August 16 2024 03:19 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 14.5 (Build 23F79) |
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 | 3.67 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 192.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1118
207.9 IPS |
|
Image Classification (HP)
|
100% |
1044
194.1 IPS |
|
Image Classification (Q)
|
99% |
1001
186.7 IPS |
|
Image Segmentation (SP)
|
100% |
16464
266.9 IPS |
|
Image Segmentation (HP)
|
100% |
16895
273.9 IPS |
|
Image Segmentation (Q)
|
100% |
15993
259.3 IPS |
|
Pose Estimation (SP)
|
100% |
133147
155.4 IPS |
|
Pose Estimation (HP)
|
100% |
137463
160.4 IPS |
|
Pose Estimation (Q)
|
96% |
116830
136.9 IPS |
|
Object Detection (SP)
|
100% |
5894
467.5 IPS |
|
Object Detection (HP)
|
100% |
5978
474.2 IPS |
|
Object Detection (Q)
|
92% |
4957
395.7 IPS |
|
Face Detection (SP)
|
100% |
28611
340.0 IPS |
|
Face Detection (HP)
|
100% |
29130
346.1 IPS |
|
Face Detection (Q)
|
100% |
21150
251.3 IPS |
|
Depth Estimation (SP)
|
100% |
34007
262.0 IPS |
|
Depth Estimation (HP)
|
99% |
35858
276.3 IPS |
|
Depth Estimation (Q)
|
97% |
35680
275.9 IPS |
|
Style Transfer (SP)
|
100% |
219961
282.8 IPS |
|
Style Transfer (HP)
|
100% |
220567
283.5 IPS |
|
Style Transfer (Q)
|
100% |
214903
276.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
25282
933.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
25825
953.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
18061
669.1 IPS |
|
Text Classification (SP)
|
100% |
545
727.2 IPS |
|
Text Classification (HP)
|
100% |
602
802.9 IPS |
|
Text Classification (Q)
|
93% |
599
803.8 IPS |
|
Machine Translation (SP)
|
100% |
1941
33.4 IPS |
|
Machine Translation (HP)
|
96% |
2124
36.7 IPS |
|
Machine Translation (Q)
|
98% |
2133
36.9 IPS |