Get started Gemma 2 Locally on Mac using MLX

In this video, we'll explore how to convert and run Google's Gemma 2 language model locally on your Mac using the MLX framework. You'll learn:
- What Google Gemma 2 is and its variants
- How to convert a Hugging Face/PyTorch model to MLX
- Steps to run Gemma 2 on your local machine
What is Google Gemma 2?
Gemma 2 is a family of lightweight, state-of-the-art open-source language models developed using the same technology behind Google's Gemini models. It comes in three sizes:
1. Gemma 2.6B
2. Gemma 9B
3. Gemma 27B
Each size is available in pre-trained and instruction-tuned variants.
Is Google Gemma 2 free?
Yes, Gemma 2 is completely open-source and accessible through the Hugging Face Hub.
Model Weights
- Quantized for MLX: huggingface.co...
- Full Precision: huggingface.co...
Additional Resources
- Gemma 2 MLX Conversion Script:github.com/Bla...
- Gemma 2 Transformers Implementation: github.com/hug...
- Gemma 2 PyTorch Implementation: github.com/goo...
- Fine-tuning Gemma Guide: unsloth.ai/blo...
- Gradio App for MLX: github.com/SOS...
Connect with Me
- LinkedIn: / prince-canuma
- Twitter: / prince_canuma
- Medium: / prince-canuma

[@MaziyarPanahi]

A complete walk through! Thank you. king!

[@princecanuma]

My pleasure @MaziyarPanahi

[@skanderbegvictor6487]

Subscribed, been following you on twitter, I am currently trying to write custom kernels for graph machine learning in mlx and am stuck.

[@princecanuma]

Great to hear 👌🏽 keep up the good work

[@gokayfem]

lets go king!!

[@princecanuma]

Let’s go 🚀