mlx-community/Mistral-7B-v0.3-4bit

The Model mlx-community/Mistral-7B-v0.3-4bit was converted to MLX format from mistralai/Mistral-7B-v0.3 using mlx-lm version 0.13.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mistral-7B-v0.3-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)