Instructions to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-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 AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

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 AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

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 AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtticusG3/Qwopus3.6-27B-Fusion-heretic-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": "AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

Ollama
How to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF with Ollama:
```
ollama run hf.co/AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M
```
Unsloth Desktop

How to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-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 AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M
```

Lemonade

How to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwopus3.6-27B-Fusion-heretic-MTP-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-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 AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

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 AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AtticusG3/Qwopus3.6-27B-Fusion-heretic-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 AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M

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 "AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF:Q4_K_M" \
  --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"

Qwopus3.6-27B-Fusion-heretic-MTP-GGUF / README.md

AtticusG3

Update README.md

0520fb3 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

4.99 kB

metadata

license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
language:
  - en
base_model:
  - KyleHessling1/Qwopus3.6-27B-Fusion-BF16
pipeline_tag: text-generation
library_name: gguf
tags:
  - gguf
  - quantized
  - llama.cpp
  - qwen3
  - qwen35
  - code
  - reasoning
  - abliterated
  - heretic
  - uncensored
  - mtp
  - imatrix
  - merge
quantized_by: AtticusG3

Qwopus3.6-27B-Fusion-heretic-MTP (GGUF)

Imatrix-guided GGUF quants of KyleHessling1/Qwopus3.6-27B-Fusion-BF16 after Heretic abliteration, with MTP / NextN heads preserved.

Base model credit: Fusion is Kyle Hessling’s reasoning⊕coding merge of Qwen3.6-27B lineage. This repo only adds Heretic abliteration + GGUF packaging. See the Fusion BF16 card for merge method, benchmarks, and intended use.

Files

File	Quant	Approx. size	Notes
`Qwopus3.6-27B-Fusion-heretic-MTP-F16.gguf`	F16	~51 GB	Full-precision GGUF (conversion source)
`Qwopus3.6-27B-Fusion-heretic-MTP-Q8_0.gguf`	Q8_0	~28 GB	High-fidelity; also used as imatrix host
`Qwopus3.6-27B-Fusion-heretic-MTP-Q5_K_M.gguf`	Q5_K_M	~19 GB	Imatrix-guided; strong quality/size
`Qwopus3.6-27B-Fusion-heretic-MTP-Q4_K_M.gguf`	Q4_K_M	~16 GB	Imatrix-guided; good default on 24–32 GB GPUs

Recommendation: start with Q4_K_M or Q5_K_M. Use Q8_0 / F16 if you are re-quantizing or measuring ceiling quality.

What changed vs Fusion BF16

Heretic abliteration (v1.4.0) on the BF16 weights
- 200 optimization trials
- Scorers: KeywordRate + KLDivergence
- Eval sets: mlabonne/harmful_behaviors + mlabonne/harmless_alpaca
- Selected trial 77: refusal keywords 89 → 3 / 100, KL divergence 0.026
- Across trials: KL mean ≈ 0.008, max ≈ 0.073 (no trial > 0.1)
MTP / NextN preserved in the GGUF (blk.64 / nextn tensors bundled). Heretic’s merge-save dropped MTP safetensors; those tensors were grafted back from Fusion BF16 before convert.
Chat template: Fusion’s native template (not a Compat rewrite).
Quantization: llama.cpp convert → Q8_0 → imatrix (WikiText-2 calib, 100×256 chunks) → Q4_K_M and Q5_K_M with --imatrix.

Abliteration reduces refusal behavior; it does not remove your responsibility for how you use the model. Follow applicable law and the Qwen license.

Quick start

llama.cpp

./llama-server \
  -m Qwopus3.6-27B-Fusion-heretic-MTP-Q4_K_M.gguf \
  -ngl 99 -c 32768 --jinja \
  --spec-type draft-mtp --spec-draft-n-max 4

LM Studio / koboldcpp / etc.

Import the .gguf of your choice. Prefer builds that understand Qwen3.6 / qwen35 and MTP speculative decoding if you want draft speedups.

OpenAI-compatible (example)

Point any OpenAI-compatible client at a llama-server / llama-swap endpoint serving one of these files. Thinking mode follows the Fusion / Qwen3.6 chat template (enable_thinking / jinja).

Model details


Parameters	~27B
Architecture	Qwen3.6 / qwen35 hybrid (linear + periodic full attention)
Context	Up to 262,144 native (practical limit = VRAM + KV cache)
Vision	Not included in these text GGUFs (BF16 Fusion retains vision tensors)
MTP	Included (NextN / draft head)
License	Qwen (see license link in YAML)

Provenance

Step	Source / tool
Base	KyleHessling1/Qwopus3.6-27B-Fusion-BF16
Abliteration	Heretic v1.4.0
Convert / quant / imatrix	llama.cpp
Uploader	AtticusG3

Limitations

Smoke-tested for generation on a small LiveCodeBench prompt sample after quant; not a full re-benchmark of Fusion’s published scores.
Some MTP (blk.64) tensors lacked imatrix entries and fell back to plain K-quants.
Uncensored / abliterated models can produce disallowed content more readily than the stock chat model — use with care.

Acknowledgements

Kyle Hessling — Fusion merge and BF16 release
Qwen team — Qwen3.6-27B
p-e-w / Heretic — abliteration tooling
llama.cpp contributors — GGUF convert, imatrix, quantize

Citation

@misc{qwopus36-fusion-heretic-mtp-gguf,
  title        = {Qwopus3.6-27B-Fusion-heretic-MTP GGUF},
  author       = {AtticusG3},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/AtticusG3/Qwopus3.6-27B-Fusion-heretic-MTP-GGUF}},
  note         = {Heretic abliteration of KyleHessling1/Qwopus3.6-27B-Fusion-BF16; imatrix GGUF quants}
}