User | jonvharrison |
Upload Date | December 08 2024 05:05 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | Mac Studio (2023) |
Model ID | Mac14,13 |
Motherboard | Mac14,13 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1390
258.6 IPS |
|
Image Classification (HP)
|
100% |
13997
2.60 KIPS |
|
Image Classification (Q)
|
96% |
16504
3.08 KIPS |
|
Image Segmentation (SP)
|
100% |
1670
27.1 IPS |
|
Image Segmentation (HP)
|
100% |
19474
315.7 IPS |
|
Image Segmentation (Q)
|
99% |
24460
396.5 IPS |
|
Pose Estimation (SP)
|
100% |
13029
15.2 IPS |
|
Pose Estimation (HP)
|
100% |
106380
124.1 IPS |
|
Pose Estimation (Q)
|
95% |
104236
122.2 IPS |
|
Object Detection (SP)
|
100% |
1702
135.0 IPS |
|
Object Detection (HP)
|
99% |
15577
1.24 KIPS |
|
Object Detection (Q)
|
91% |
17256
1.38 KIPS |
|
Face Detection (SP)
|
100% |
3515
41.8 IPS |
|
Face Detection (HP)
|
100% |
35961
427.3 IPS |
|
Face Detection (Q)
|
100% |
45710
543.1 IPS |
|
Depth Estimation (SP)
|
100% |
6291
48.5 IPS |
|
Depth Estimation (HP)
|
99% |
87484
674.0 IPS |
|
Depth Estimation (Q)
|
85% |
109760
857.7 IPS |
|
Style Transfer (SP)
|
100% |
25095
32.3 IPS |
|
Style Transfer (HP)
|
100% |
202986
260.9 IPS |
|
Style Transfer (Q)
|
96% |
190591
245.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5086
187.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
40880
1.51 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48877
1.80 KIPS |
|
Text Classification (SP)
|
100% |
2281
3.04 KIPS |
|
Text Classification (HP)
|
100% |
4001
5.34 KIPS |
|
Text Classification (Q)
|
93% |
3960
5.31 KIPS |
|
Machine Translation (SP)
|
100% |
4629
79.7 IPS |
|
Machine Translation (HP)
|
100% |
4886
84.2 IPS |
|
Machine Translation (Q)
|
98% |
5580
96.4 IPS |