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

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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-oMLX-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

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

Run Hermes

hermes

Atomic Chat

OpenClaw

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

This repository is packaged specifically for oMLX native MTP. The target checkpoint's main safetensors index includes all 15 language_model.mtp.* tensors, which bind directly to oMLX's Qwen3.5/3.6 VLM MTP model tree.

Recommended MTP runtime: use this oMLX artifact for MTP. oMLX provides the faster, more mature integrated path for this model and requires no separate drafter.

oMLX

Add this model repository to oMLX and enable Native MTP in the model settings. No separate draft-model repository is required for this oMLX artifact.

Compatibility

Runtime	Recommended artifact
oMLX	This repository: embedded/indexed `language_model.mtp.*` target
Direct `mlx-vlm`	Use the normal 4-bit target plus the standalone direct `mlx-vlm` MTP drafter
LM Studio MLX	Use the normal 4-bit target without MTP; runtime `1.10.1` does not support draft models for this batched VLM
MTPLX	Use the MTPLX sidecar target

Do not use this embedded-MTP target as an LM Studio target: LM Studio's current MLX target loader and oMLX use different MTP packaging contracts.

Verified runtime

Verified end-to-end on Apple Silicon with oMLX 0.4.4rc1: the model loaded directly through VLMBatchedEngine, oMLX reported its native MTP patch active, and a bounded chat generation completed with the MTP path active. That smoke accepted 2 of 5 drafted tokens (40%); acceptance depends on the prompt.

Technical details

Target trunk: MLX affine 4-bit, group size 64
MTP tensors: 15 language_model.mtp.* entries in the main model.safetensors.index.json
MTP precision: BF16
Source revision: 44f63da8141407af529405c1e4b83fa39b70abe0
The three previously validated target trunk shards are unchanged; the MTP payload is an additional indexed shard.