User | technotim |
Upload Date | December 18 2024 04:46 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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 | 3.39 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1272
236.5 IPS |
|
Image Classification (HP)
|
100% |
14084
2.62 KIPS |
|
Image Classification (Q)
|
96% |
16887
3.15 KIPS |
|
Image Segmentation (SP)
|
100% |
1571
25.5 IPS |
|
Image Segmentation (HP)
|
100% |
19324
313.3 IPS |
|
Image Segmentation (Q)
|
99% |
23662
383.6 IPS |
|
Pose Estimation (SP)
|
100% |
11248
13.1 IPS |
|
Pose Estimation (HP)
|
100% |
107235
125.1 IPS |
|
Pose Estimation (Q)
|
95% |
106132
124.4 IPS |
|
Object Detection (SP)
|
100% |
1537
121.9 IPS |
|
Object Detection (HP)
|
99% |
15699
1.25 KIPS |
|
Object Detection (Q)
|
91% |
17145
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3053
36.3 IPS |
|
Face Detection (HP)
|
100% |
31882
378.8 IPS |
|
Face Detection (Q)
|
100% |
40355
479.5 IPS |
|
Depth Estimation (SP)
|
100% |
5492
42.3 IPS |
|
Depth Estimation (HP)
|
99% |
86948
669.9 IPS |
|
Depth Estimation (Q)
|
85% |
110163
860.9 IPS |
|
Style Transfer (SP)
|
100% |
23479
30.2 IPS |
|
Style Transfer (HP)
|
100% |
205142
263.7 IPS |
|
Style Transfer (Q)
|
96% |
196166
253.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4757
175.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
42559
1.57 KIPS |
|
Image Super-Resolution (Q)
|
99% |
51337
1.90 KIPS |
|
Text Classification (SP)
|
100% |
2161
2.88 KIPS |
|
Text Classification (HP)
|
100% |
3784
5.05 KIPS |
|
Text Classification (Q)
|
93% |
3787
5.08 KIPS |
|
Machine Translation (SP)
|
100% |
4008
69.0 IPS |
|
Machine Translation (HP)
|
100% |
3292
56.7 IPS |
|
Machine Translation (Q)
|
98% |
3436
59.4 IPS |