Live 113: Google Gemma on Apple Silicon Macs with Python & the Hugging Face CLI

---

In Live 113, we ran Google's Gemma LLM 2B- and 7B-parameter open models on an Apple Silicon Mac, both on the CPU and the GPU.

We downloaded the Instruct models with the Hugging Face CLI and used PyTorch with Hugging Face's Transformers and Accelerate Python packages to run Gemma locally.

---

If this is something that interests you, please let me know on Twitter or, even better, on the Discord community.

Thanks for watching.

See you next time!

Chapters

01:23 · Introduction
02:46 · Previously
03:11 · Today
03:45 · Elgato Prompter
06:19 · Interlude
06:43 · Google Gemma 2B & 7B
08:45 · Overview
11:59 · Hugging Face CLI
14:01 · CLI Install
14:54 · CLI Login
15:33 · Download Gemma
22:19 · Run Gemma Locally
24:49 · Anaconda Environment
29:00 · Gemma on the CPU
52:56 · Apple Silicon GPUs
55:32 · List Torch Silicon MPS Device
56:50 · Gemma on Apple Silicon GPUs
01:08:16 · Sync Samples to Git
01:17:22 · Thumbnail
01:28:42 · Links
01:31:12 · Chapters
01:36:28 · Outro