# Running transformer models on mps instead of cpu on mac

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-transformer-models-on-mps-instead-of-cpu-on-mac%2F86967%3E%5C
**Category:** Beginners\
**Created:** [May 16, 2024, 7:47am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-transformer-models-on-mps-instead-of-cpu-on-mac%2F86967 "2024-05-16T07:47:20Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![msheikhzadeh](https://avatars.discourse-cdn.com/v4/letter/m/e47c2d/32.png) [@msheikhzadeh](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmsheikhzadeh)%5C
**Post date:** [May 16, 2024, 7:47am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-transformer-models-on-mps-instead-of-cpu-on-mac%2F86967%2F1 "2024-05-16T07:47:20Z")

</div>

I have an Macbook pro with M3 Max chip, 40 GPU cores, and 64GB of RAM. I am looking for a tutorial, resource, which can help me run my models on mps (macs GPU) instead of on CPU (I used transformers so far only for inference, but I may want to fine-tune them in the future).

I should say, I am new to the transformers and I hope this is not a too-basic question.

---

<div class="post-metadata">

**Author:** ![Sidewinder99](https://avatars.discourse-cdn.com/v4/letter/s/5e9695/32.png) [@Sidewinder99](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSidewinder99)%5C
**Post date:** [January 18, 2025, 10:10am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Frunning-transformer-models-on-mps-instead-of-cpu-on-mac%2F86967%2F2 "2025-01-18T10:10:02Z")

</div>

If you haven’t found this already, [GitHub - domschl/HuggingFaceGuidedTourForMac: A guided tour on how to use HuggingFace large language models on Macs with Apple Silicon](https://github.com/domschl/HuggingFaceGuidedTourForMac?tab=readme-ov-file#readme)
