README.md

metadata

license: gemma
library_name: mlx
pipeline_tag: text-generation
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
  To access Gemma on Hugging Face, you’re required to review and agree to
  Google’s usage license. To do this, please ensure you’re logged in to Hugging
  Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
base_model: mlx-community/gemma-3-12b-it-bf16
tags:
  - mlx

mlx-community/gemma-3-text-12b-it-4bit

The Model mlx-community/gemma-3-text-12b-it-4bit was converted to MLX format from mlx-community/gemma-3-12b-it-bf16 using mlx-lm version 0.22.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-3-text-12b-it-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)