Easy way to run local LLM for your M-series Macbooks

run_llama.sh

#!/usr/bin/env bash

# Install Git Large File Storage (LFS)
brew install git-lfs
git lfs install

# Download & Install Llama
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
LLAMA_METAL=1 make -j # build with Metal support for (M-series) Apple Silicon

## Download Models
cd models
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/TheBloke/guanaco-7B-GGML
cd guanaco-7B-GGML
git lfs pull --include "guanaco-7B.ggmlv3.q4_0.bin" 
cd ../..

## Run Llama
./main -m ./models/guanaco-7B-GGML/guanaco-7B.ggmlv3.q4_0.bin -p "Python code for adding 2 numbers is" --ignore-eos -n 256 -ngl 1