ML on Mac: Peformance without CUDA

Home

Blog

Projects

Patrons

rss

Loading search...

2026

AI agents, compounding, and COVID vibes

In browser eye tracking with WebGazer

MDX Canvas Host Demo

2025

Fast gaussian splats from a single image

I am unfinished by design

Ring Doorbell Hacking

2024

Even More AI Video on Consumer Hardware

More AI Video generation on consumer hardware

AI Video generation on consumer hardware

Strategy for the good life

SDXL LoRa Training

Making sense of voices

Voice Cloning and TTS with F5

Designing a website

Feedback on your UX research

andremolnar.com V6

2023

ML on Mac: Peformance without CUDA

People Detection and Segmentation

Machine Learn all the things

tl;dr;

Written by Andre Molnar 2023-05-21

apple

coreml

machine learning

mac

cuda

pytorch

tensorflow

No CUDA, no problem. You can still train and run ML models on your Mac with CoreML. You can even convert your PyTorch and TensorFlow models to CoreML models.

Apple Machine Learning

https://coremltools.readme.io/docs/unified-conversion-api

And you can run predictions
Images need to be PIL images, not numpy arrays.

https://coremltools.readme.io/docs/model-prediction

Loading blog post...