mlx-community/TinyMistral-248M-8bits

The Model mlx-community/TinyMistral-248M-8bits was converted to MLX format from Locutusque/TinyMistral-248M using mlx-lm version 0.14.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/TinyMistral-248M-8bits")
response = generate(model, tokenizer, prompt="hello", verbose=True)