Instructions to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF",
	filename="q8_0-v1.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

Use Docker

docker model run hf.co/markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

Ollama
How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with Ollama:
```
ollama run hf.co/markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0
```

Unsloth Studio

How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF to start chatting

How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

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 markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

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 "markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

Docker Model Runner
How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0
```

Lemonade

How to use markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF:Q8_0

Run and chat with the model

lemonade run user.Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF-Q8_0

List all available models

lemonade list

This repository represents an effort to graft and re-train an MTP layer for DavidAU's Qwen3.6-40B model, inspired by Piehsoft's untrained MTP grafts.

Currently only offering q8_0 quantizations, but this will eventually expand once MTP retraining is finalized.

Version 1 (complete)

A simple retraining attempt that used the following procedure:

Ran the 40B model on 117 random prompts
Record what it was thinking at every position by introspecting llama.cpp
- Specifically, recorded which 64 tokens it thought were most likely next and how confident it was in each.
- Note: Substituted h_t with embedding(input_token) to move forward with the data that was immediately accessible.
Use the recorded data to retrain the MTP layer: align what the MTP's predictions with reality
- This data did not include hidden states, but since the trained head is shown real-world verifier logprobs during training its bias toward the most common tokens is effectively re-calibrated.

Compared to Piehsoft's untrained MTP head, this methodology

Significantly improved acceptances rates in structured text / coding scenarios
Provided little to no impact on high-entropy scenarios such as creative writing / casual chat.

Ultimately proved that improving acceptance rates via retraining was possible. Further improvements seem to require:

Larger corpus (dataset)
Higher text entropy within corpus
Most importantly, data collection of the verifier hidden states

Version 2 (in-progress)

EDIT: Training using hidden states ended up generating significantly worse results than the methodology used in v1. Alternative paths are being considered, but this may potentially end as a stalemate.

~~Training is in-progress, which builds on-top of the v1. This version likely won't be a final version, but rather will be used to help steer direction. The main changes will be:~~

~~Collect data using a modified version of llama.cpp that exposes data from the 40B model's hidden states (h_t)~~
~~Use a dataset with high entropy: WildChat-1M~~
- ~~Not training on the full dataset (would take a long time), will use a subset of randomly selected samples.~~
~~Increase epochs from 3 to 5 (and tweak a few other training settings)~~

Downloads last month: 2,250

GGUF

Model size

39B params

Architecture

qwen35

Hardware compatibility

8-bit

Model tree for markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF

Base model

Qwen/Qwen3.6-27B

Finetuned

DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking

Quantized

DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF

Quantized

(4)

this model

Quantizations

2 models

markmonger
/

Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF

Version 1 (complete)

Version 2 (in-progress)

Model tree for markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF

Datasets used to train markmonger/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-iMatrix-MTP-GGUF