README.md

metadata

license: gemma
tags:
  - gemma3
  - gemma
  - google
  - mlx
pipeline_tag: text-generation
library_name: mlx
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: google/gemma-3-270m

NexVeridian/gemma-3-270m-6bit

This model NexVeridian/gemma-3-270m-6bit was converted to MLX format from google/gemma-3-270m using mlx-lm version 0.26.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("NexVeridian/gemma-3-270m-6bit")

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)