mlx-community/gemma-2-9b-it-8bit

The Model mlx-community/gemma-2-9b-it-8bit was converted to MLX format from google/gemma-2-9b-it using mlx-lm version 0.15.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-2-9b-it-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)