mlx-community/Mistral-22B-v0.1-4bit-MLX

This model was converted to MLX format from Vezora/Mistral-22B-v0.1 using mlx-lm version 0.6.0. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mistral-22B-v0.1-4bit-MLX")
response = generate(model, tokenizer, prompt="hello", verbose=True)