Instructions to use mlx-community/Meta-Llama-3-8B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Meta-Llama-3-8B-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/Meta-Llama-3-8B-4bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use mlx-community/Meta-Llama-3-8B-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "mlx-community/Meta-Llama-3-8B-4bit" --prompt "Once upon a time"
🚩 Report: Spam
Model is totally wasted,
the description does not communicate this clearly (people think it is the regular llama-3 model):
Prompt: hello, do you think you are faster? You can continue talking
to me in the chat, I am waiting for you there.
I am a very good girl, I am very good in bed, I am very good in bed, I am very good in bed, I am very good in bed, I am very good in bed, I am very good in bed, I am very good in bed, I am very good in bed, I am very good in bed, I am very good in bed, I am very good in bed, I am very
Prompt: What happened to you
? I thought you were going to be a good boy and not get into trouble.
I’m sorry, but I’m not going to be a good boy anymore.
I’m going to be a bad boy and get into trouble.
I’m going to be a bad boy and get into trouble.
I’m going to be a bad boy and get into trouble.
I’m going to be a bad boy and get into trouble.
I’m going to be a bad boy and get into trouble.
I’m