README.md

metadata

license: apache-2.0
base_model: Goekdeniz-Guelmez/Gabliterated-Qwen3-0.6B
pipeline_tag: text-generation
library_name: mlx
tags:
  - uncensored
  - code
  - legal
  - text-generation-inference
  - mlx

mlx-community/Gabliterated-Qwen3-0.6B-6bit

This model mlx-community/Gabliterated-Qwen3-0.6B-6bit was converted to MLX format from Goekdeniz-Guelmez/Gabliterated-Qwen3-0.6B using mlx-lm version 0.25.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Gabliterated-Qwen3-0.6B-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)