User | Gonfonix |
Upload Date | November 10 2024 02:03 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Ultra |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | Mac Pro (2023) |
Model ID | Mac14,8 |
Motherboard | Mac14,8 |
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% |
6312
1.17 KIPS |
|
Image Classification (HP)
|
100% |
6356
1.18 KIPS |
|
Image Classification (Q)
|
97% |
5660
1.06 KIPS |
|
Image Segmentation (SP)
|
100% |
17806
288.6 IPS |
|
Image Segmentation (HP)
|
100% |
18468
299.4 IPS |
|
Image Segmentation (Q)
|
99% |
19000
308.0 IPS |
|
Pose Estimation (SP)
|
100% |
138274
161.3 IPS |
|
Pose Estimation (HP)
|
100% |
142623
166.4 IPS |
|
Pose Estimation (Q)
|
95% |
130358
152.8 IPS |
|
Object Detection (SP)
|
100% |
6289
498.8 IPS |
|
Object Detection (HP)
|
100% |
6304
500.1 IPS |
|
Object Detection (Q)
|
91% |
5657
452.0 IPS |
|
Face Detection (SP)
|
100% |
34968
415.5 IPS |
|
Face Detection (HP)
|
100% |
34918
414.9 IPS |
|
Face Detection (Q)
|
100% |
26156
310.8 IPS |
|
Depth Estimation (SP)
|
100% |
34876
268.7 IPS |
|
Depth Estimation (HP)
|
99% |
36845
283.9 IPS |
|
Depth Estimation (Q)
|
85% |
31999
250.1 IPS |
|
Style Transfer (SP)
|
100% |
226593
291.3 IPS |
|
Style Transfer (HP)
|
100% |
229322
294.8 IPS |
|
Style Transfer (Q)
|
96% |
213587
275.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
25769
951.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
26312
971.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
21035
776.7 IPS |
|
Text Classification (SP)
|
100% |
2352
3.14 KIPS |
|
Text Classification (HP)
|
100% |
4056
5.41 KIPS |
|
Text Classification (Q)
|
93% |
4030
5.41 KIPS |
|
Machine Translation (SP)
|
100% |
2208
38.0 IPS |
|
Machine Translation (HP)
|
100% |
2169
37.4 IPS |
|
Machine Translation (Q)
|
98% |
2076
35.9 IPS |