I put the latest Apple Silicon Macs (M3, M3 Pro, M3 Max) M3 series Macs through a series of machine learning speed tests with PyTorch and TensorFlow.
Code on GitHub - https://github.com/mrdbourke/mac-ml-s...
Blog post write up - https://www.mrdbourke.com/apple-m3-ma...
Learn ML (taught by me) - https://www.mrdbourke.com/ml-courses/
Links mentioned:
MLX framework by Apple - https://github.com/ml-explore/mlx
llama-cpp-python - https://github.com/abetlen/llama-cpp-...
Other links:
Download Nutrify for iOS - https://www.nutrify.app
Learn AI/ML (beginner-friendly course) - https://dbourke.link/ZTMMLcourse
Learn TensorFlow - https://dbourke.link/ZTMTFcourse
Learn PyTorch - https://dbourke.link/ZTMPyTorch
AI/ML courses/books I recommend - https://www.mrdbourke.com/ml-resources/
Read my novel Charlie Walks - https://www.charliewalks.com
Connect elsewhere:
Web - https://www.mrdbourke.com
Twitter - / mrdbourke
LinkedIn - / mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro
0:33 - What to look for in a PC for ML
1:09 - Machines that we’re testing (M1 Pro, M3, M3 Pro, M3 Max, Nvidia TITAN RTX, Google Colab)
1:48 - Models and memory requirements
2:22 - My machine learning workflow
2:39 - Experiments we’re running
3:14 - Resources
3:58 - PyTorch ResNet50 CIFAR100 results
6:10 - PyTorch ResNet50 Food101 results
8:21 - PyTorch DistilBERT IMDB results
10:32 - TensorFlow ResNet50 CIFAR100 results
12:19 - TensorFlow ResNet50 Food101 results
13:30 - TensorFlow SmallTransformer IMDB results
14:55 - Llama CPP Python results
16:30 - Geekbench ML results
19:24 - Discussion
21:09 - Recommendations for ML
23:00 - Extras
#machinelearning #m3