User | non |
Upload Date | September 22 2024 10:09 AM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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 | 3.45 GHz |
Cluster 1 | 16 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5975
1.11 KIPS |
|
Image Classification (HP)
|
100% |
6058
1.13 KIPS |
|
Image Classification (Q)
|
97% |
5369
1.00 KIPS |
|
Image Segmentation (SP)
|
100% |
16106
261.1 IPS |
|
Image Segmentation (HP)
|
100% |
16383
265.6 IPS |
|
Image Segmentation (Q)
|
99% |
16841
273.0 IPS |
|
Pose Estimation (SP)
|
100% |
106319
124.1 IPS |
|
Pose Estimation (HP)
|
100% |
111248
129.8 IPS |
|
Pose Estimation (Q)
|
95% |
102036
119.6 IPS |
|
Object Detection (SP)
|
100% |
6098
483.7 IPS |
|
Object Detection (HP)
|
100% |
6166
489.1 IPS |
|
Object Detection (Q)
|
91% |
5487
438.4 IPS |
|
Face Detection (SP)
|
100% |
32045
380.8 IPS |
|
Face Detection (HP)
|
100% |
31753
377.3 IPS |
|
Face Detection (Q)
|
100% |
25041
297.5 IPS |
|
Depth Estimation (SP)
|
100% |
32937
253.8 IPS |
|
Depth Estimation (HP)
|
99% |
34786
268.0 IPS |
|
Depth Estimation (Q)
|
85% |
29803
232.9 IPS |
|
Style Transfer (SP)
|
100% |
193196
248.4 IPS |
|
Style Transfer (HP)
|
100% |
199984
257.1 IPS |
|
Style Transfer (Q)
|
96% |
185227
239.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
23352
862.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
23840
880.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
19459
718.5 IPS |
|
Text Classification (SP)
|
100% |
2227
2.97 KIPS |
|
Text Classification (HP)
|
100% |
3862
5.16 KIPS |
|
Text Classification (Q)
|
93% |
3842
5.16 KIPS |
|
Machine Translation (SP)
|
100% |
2067
35.6 IPS |
|
Machine Translation (HP)
|
100% |
2039
35.1 IPS |
|
Machine Translation (Q)
|
98% |
1886
32.6 IPS |