User | Barritz |
Upload Date | May 16 2025 02:50 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (16-inch, 2021) |
Model ID | MacBookPro18,2 |
Motherboard | MacBookPro18,2 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5183
963.8 IPS |
|
Image Classification (HP)
|
100% |
5324
990.1 IPS |
|
Image Classification (Q)
|
96% |
4796
895.7 IPS |
|
Image Segmentation (SP)
|
100% |
11845
192.0 IPS |
|
Image Segmentation (HP)
|
100% |
12231
198.3 IPS |
|
Image Segmentation (Q)
|
99% |
11614
188.3 IPS |
|
Pose Estimation (SP)
|
100% |
57149
66.7 IPS |
|
Pose Estimation (HP)
|
100% |
62324
72.7 IPS |
|
Pose Estimation (Q)
|
96% |
59369
69.5 IPS |
|
Object Detection (SP)
|
100% |
5256
416.9 IPS |
|
Object Detection (HP)
|
100% |
5417
429.7 IPS |
|
Object Detection (Q)
|
92% |
5058
403.7 IPS |
|
Face Detection (SP)
|
100% |
21083
250.5 IPS |
|
Face Detection (HP)
|
100% |
21348
253.7 IPS |
|
Face Detection (Q)
|
100% |
18934
225.0 IPS |
|
Depth Estimation (SP)
|
100% |
26457
203.8 IPS |
|
Depth Estimation (HP)
|
99% |
27954
215.4 IPS |
|
Depth Estimation (Q)
|
86% |
25689
200.7 IPS |
|
Style Transfer (SP)
|
100% |
96181
123.6 IPS |
|
Style Transfer (HP)
|
100% |
122397
157.3 IPS |
|
Style Transfer (Q)
|
96% |
118876
153.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
17004
627.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
17857
659.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
15678
578.9 IPS |
|
Text Classification (SP)
|
100% |
2293
3.06 KIPS |
|
Text Classification (HP)
|
100% |
4061
5.42 KIPS |
|
Text Classification (Q)
|
93% |
4043
5.43 KIPS |
|
Machine Translation (SP)
|
100% |
1880
32.4 IPS |
|
Machine Translation (HP)
|
100% |
1952
33.6 IPS |
|
Machine Translation (Q)
|
98% |
1805
31.2 IPS |