User | richh- |
Upload Date | February 05 2025 12:32 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D60) |
Model | MacBook Pro (16-inch, 2023) |
Model ID | Mac14,6 |
Motherboard | Mac14,6 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.28 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 96.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1352
251.5 IPS |
|
Image Classification (HP)
|
100% |
15568
2.90 KIPS |
|
Image Classification (Q)
|
96% |
18044
3.37 KIPS |
|
Image Segmentation (SP)
|
100% |
1684
27.3 IPS |
|
Image Segmentation (HP)
|
100% |
19489
315.9 IPS |
|
Image Segmentation (Q)
|
99% |
24516
397.4 IPS |
|
Pose Estimation (SP)
|
100% |
12012
14.0 IPS |
|
Pose Estimation (HP)
|
100% |
107539
125.5 IPS |
|
Pose Estimation (Q)
|
95% |
106420
124.7 IPS |
|
Object Detection (SP)
|
100% |
1664
132.0 IPS |
|
Object Detection (HP)
|
99% |
16601
1.32 KIPS |
|
Object Detection (Q)
|
91% |
18353
1.47 KIPS |
|
Face Detection (SP)
|
100% |
3580
42.5 IPS |
|
Face Detection (HP)
|
100% |
33797
401.6 IPS |
|
Face Detection (Q)
|
100% |
44989
534.6 IPS |
|
Depth Estimation (SP)
|
100% |
6005
46.3 IPS |
|
Depth Estimation (HP)
|
99% |
87881
677.1 IPS |
|
Depth Estimation (Q)
|
85% |
109763
857.8 IPS |
|
Style Transfer (SP)
|
100% |
23797
30.6 IPS |
|
Style Transfer (HP)
|
100% |
209399
269.2 IPS |
|
Style Transfer (Q)
|
96% |
196605
253.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5014
185.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
44054
1.63 KIPS |
|
Image Super-Resolution (Q)
|
99% |
53138
1.96 KIPS |
|
Text Classification (SP)
|
100% |
2224
2.97 KIPS |
|
Text Classification (HP)
|
100% |
3812
5.09 KIPS |
|
Text Classification (Q)
|
93% |
3835
5.15 KIPS |
|
Machine Translation (SP)
|
100% |
4507
77.6 IPS |
|
Machine Translation (HP)
|
100% |
3561
61.3 IPS |
|
Machine Translation (Q)
|
98% |
3770
65.1 IPS |