Instructions to use TheCluster/Qwen3.6-27B-Heretic-MLX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheCluster/Qwen3.6-27B-Heretic-MLX-bf16 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("TheCluster/Qwen3.6-27B-Heretic-MLX-bf16")
config = load_config("TheCluster/Qwen3.6-27B-Heretic-MLX-bf16")

# 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 TheCluster/Qwen3.6-27B-Heretic-MLX-bf16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TheCluster/Qwen3.6-27B-Heretic-MLX-bf16"

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": "TheCluster/Qwen3.6-27B-Heretic-MLX-bf16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TheCluster/Qwen3.6-27B-Heretic-MLX-bf16 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 "TheCluster/Qwen3.6-27B-Heretic-MLX-bf16"

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 TheCluster/Qwen3.6-27B-Heretic-MLX-bf16

Run Hermes

hermes

OpenClaw new

How to use TheCluster/Qwen3.6-27B-Heretic-MLX-bf16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TheCluster/Qwen3.6-27B-Heretic-MLX-bf16"

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 "TheCluster/Qwen3.6-27B-Heretic-MLX-bf16" \
  --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"

Qwen3.6-27B Heretic

This is an uncensored version of Qwen/Qwen3.6-27B, made using Heretic v1.2.0.

Quality: original (bfloat16)

Most tensors use 8-bit affine quantization with a group size 32; some important tensors are saved in bf16.

Abliteration method: Arbitrary-Rank Ablation (ARA) with row-norm preservation.

Abliteration metrics

Metric	This model	Original model (unsloth/Qwen3.6-27B)
KL divergence	0.0552	0 (by definition)
Refusals	8/100	90/100

Abliteration parameters

Parameter	Value
start_layer_index	19
end_layer_index	36
preserve_good_behavior_weight	0.3961
steer_bad_behavior_weight	0.0002
overcorrect_relative_weight	1.2029
neighbor_count	14

Recommended settings

Sampling Parameters:
- The developers suggest using the following sets of sampling parameters depending on the mode and task type:
  - Thinking mode for general tasks:
    temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
  - Thinking mode for precise coding tasks (e.g., WebDev):
    temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
  - Instruct (or non-thinking) mode for general tasks:
    temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
  - Instruct (or non-thinking) mode for reasoning tasks:
    temperature=1.0, top_p=1.0, top_k=40, min_p=0.0, presence_penalty=2.0, repetition_penalty=1.0
- For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.

Source

This model was converted to MLX format from noclip84/Qwen3.6-27B-heretic-ARA using mlx-vlm version 0.4.4.

Downloads last month: 150

Safetensors

Model size

28B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for TheCluster/Qwen3.6-27B-Heretic-MLX-bf16

Base model

noclip84/Qwen3.6-27B-heretic-ARA

Finetuned

(1)

this model

Collection including TheCluster/Qwen3.6-27B-Heretic-MLX-bf16

Uncensored Qwen3.6 MLX

Collection

Uncensored Qwen3.6 for Apple Silicon • 16 items • Updated Apr 29 • 3