Instructions to use pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP 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("pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP")
config = load_config("pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP")

# 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 pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP"

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": "pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP 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 "pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP"

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 pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP"

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 "pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP" \
  --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"

Huihui ThinkingCap Qwen3.6 27B Abliterated — MLX 4-bit MTP

MTPLX-compatible conversion of huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated, pinned to revision 44f63da.

Runtime-specific artifact: do not load this repository in LM Studio. LM Studio flattens the MTPLX sidecar into its target directory, causing the target loader to reject the 15 mtp.* tensors. For the recommended MTP experience, use the oMLX Native-MTP model; oMLX is the faster, more mature integrated path for this model.

Trunk: MLX affine 4-bit, group size 64.
MTP head: 15-tensor BF16 sidecar at mtp/weights.safetensors.
Runtime: MTPLX 2.1.0, Apple Silicon only.

pip install -U mtplx
mtplx run --model pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP --depth 3 "Hello"

MTPLX Forge classified this artifact as verified-native. A bounded 32-token M4 Max verification measured 24.94 tok/s AR and 46.02 tok/s at MTP depth 3 (1.85x); treat this as a packaging smoke, not a general benchmark.

This is an abliterated model with reduced safety behavior. Review the upstream model card before use.

Downloads last month: 638

Safetensors

Model size

5B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP

Base model

Qwen/Qwen3.6-27B

Finetuned

bottlecapai/ThinkingCap-Qwen3.6-27B

Finetuned

huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated

Quantized

(6)

this model