Instructions to use zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6 with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6")
config = load_config("zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6

Run Hermes

hermes

OpenClaw new

How to use zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

🦆 zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6

This model was converted to MLX from wangzhang/Qwen3.6-27B-abliterated using mlx-vlm version 0.6.3. Please refer to the original model card for more details.

🌟 Quality

Mixed-precision quantized vision language model with an effective 5.092 bits per weight. Combines the size and speed benefits of a 4-bit quant with higher precision where it matters most.

mlx_vlm.convert --quantize --q-group-size 32 --quant-predicate mixed_4_6

🛠️ Customizations

This quant is aware of the current date, and also enables thinking (if available). You may disable this behavior by deleting the following line from the chat template, or changing true to false:

{%- set enable_thinking = true %}

A fix is also included for a thinking-related performance issue in Qwen 3.6.

🖥️ Use with `mlx`

pip install -U mlx-vlm

mlx_vlm.generate --model zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6 --max-tokens 100 --temperature 0 --prompt "Describe this image." --image <path_to_image>

Downloads last month: 261

Safetensors

Model size

5B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6

Base model

Qwen/Qwen3.6-27B

Finetuned

wangzhang/Qwen3.6-27B-abliterated

Quantized

(14)

this model

🦆 zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6

🌟 Quality

🛠️ Customizations

🖥️ Use with mlx

Model tree for zecanard/Qwen3.6-27B-uncensored-abliterix-MLX-4bit-mixed_4_6

🖥️ Use with `mlx`