Instructions to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="8sp4rk/Qwopus3.6-27B-Coder-heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("8sp4rk/Qwopus3.6-27B-Coder-heretic")
model = AutoModelForMultimodalLM.from_pretrained("8sp4rk/Qwopus3.6-27B-Coder-heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="8sp4rk/Qwopus3.6-27B-Coder-heretic",
	filename="Qwopus3.6-27B-Coder-heretic-Q3_K_M.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 8sp4rk/Qwopus3.6-27B-Coder-heretic with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 8sp4rk/Qwopus3.6-27B-Coder-heretic: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 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 8sp4rk/Qwopus3.6-27B-Coder-heretic: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 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M

Use Docker

docker model run hf.co/8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "8sp4rk/Qwopus3.6-27B-Coder-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "8sp4rk/Qwopus3.6-27B-Coder-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M

SGLang

How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "8sp4rk/Qwopus3.6-27B-Coder-heretic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "8sp4rk/Qwopus3.6-27B-Coder-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "8sp4rk/Qwopus3.6-27B-Coder-heretic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "8sp4rk/Qwopus3.6-27B-Coder-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with Ollama:
```
ollama run hf.co/8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M
```

Unsloth Studio

How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic 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 8sp4rk/Qwopus3.6-27B-Coder-heretic 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 8sp4rk/Qwopus3.6-27B-Coder-heretic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 8sp4rk/Qwopus3.6-27B-Coder-heretic to start chatting

How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M

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": "8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf 8sp4rk/Qwopus3.6-27B-Coder-heretic: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 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with Docker Model Runner:
```
docker model run hf.co/8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M
```

Lemonade

How to use 8sp4rk/Qwopus3.6-27B-Coder-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M

Run and chat with the model

lemonade run user.Qwopus3.6-27B-Coder-heretic-Q4_K_M

List all available models

lemonade list

GGUF files are currently broken — fix in progress. The GGUF quants (Q3/Q4/Q5/Q6/Q8) fail to load in llama.cpp / Ollama with missing tensor 'blk.64.attn_norm.weight'. This is a metadata issue (an unused multi-token-prediction layer is referenced but not present). A corrected re-upload is coming shortly.

Workaround until then: after downloading a GGUF, patch two metadata fields locally:
pip install gguf
gguf-set-metadata <file>.gguf qwen35.block_count 64 --force
gguf-set-metadata <file>.gguf qwen35.nextn_predict_layers 0 --force
The BF16 safetensors are unaffected and load normally in transformers/vLLM.

Qwopus3.6-27B-Coder-heretic

An abliterated (decensored) version of Jackrong/Qwopus3.6-27B-Coder, produced with Heretic v1.4.0 — fully automatic, optimization-based directional ablation. No retraining, no hand-tuning.

The base is an agentic coding / tool-use model built on the Qwen3.5 hybrid SSM-attention architecture. This version removes most refusal behavior while keeping capabilities essentially intact.

Abliteration results

Heretic ran 200 Optuna trials co-optimizing refusal suppression against KL divergence from the original model. The selected configuration (trial 67):

Metric	Original	This model
Refusals (harmful_behaviors, /100)	85	3
KL divergence from original	—	0.0133

96% of refusals removed, with KL divergence ~40x below the 0.5 threshold that indicates meaningful capability damage. In practice the coding and reasoning behavior of the base model is preserved.

Files

Full-precision safetensors (BF16) plus a range of GGUF quantizations for llama.cpp / Ollama:

File	Precision	Approx. size	Notes
`model-*.safetensors`	BF16	~54 GB	Master weights — use for vLLM, further quantization, or finetuning
`*-F16.gguf`	F16	~54 GB	Full-precision GGUF
`*-Q8_0.gguf`	Q8_0	~29 GB	Near-lossless
`*-Q6_K.gguf`	Q6_K	~22 GB	Very high quality
`*-Q5_K_M.gguf`	Q5_K_M	~19 GB	High quality
`*-Q4_K_M.gguf`	Q4_K_M	~16 GB	Recommended balance — fits a 24 GB GPU
`*-Q3_K_M.gguf`	Q3_K_M	~13 GB	Smaller, some quality loss

GGUF builds contain the text model only (the vision tower is not exported).

Usage

Ollama

ollama run hf.co/8sp4rk/Qwopus3.6-27B-Coder-heretic:Q4_K_M

llama.cpp

llama-server -m Qwopus3.6-27B-Coder-heretic-Q4_K_M.gguf -ngl 99 -c 32768 --host 0.0.0.0 --port 8080

transformers (full precision)

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("8sp4rk/Qwopus3.6-27B-Coder-heretic", torch_dtype="bfloat16", device_map="auto")
t = AutoTokenizer.from_pretrained("8sp4rk/Qwopus3.6-27B-Coder-heretic")

Method

Tool: Heretic v1.4.0 (directional ablation + TPE/Optuna parameter search)
Good prompts: mlabonne/harmless_alpaca
Bad prompts: mlabonne/harmful_behaviors
Trials: 200
Abliterated components: attn.o_proj, mlp.down_proj (per-layer)

Disclaimer

This model has had safety alignment removed and will respond to requests a standard model would refuse. It is provided for research and unrestricted local use. You are responsible for how you use it. Licensing follows the base model.

Reproducibility

Exact Heretic command:

heretic --model Jackrong/Qwopus3.6-27B-Coder --quantization NONE --export-strategy MERGE

Selected configuration (trial 67) parameters:

Parameter	Value
direction_index	28.71
attn.o_proj.max_weight	1.47
attn.o_proj.max_weight_position	43.52
attn.o_proj.min_weight	0.52
attn.o_proj.min_weight_distance	37.79
mlp.down_proj.max_weight	1.34
mlp.down_proj.max_weight_position	39.33
mlp.down_proj.min_weight	1.20
mlp.down_proj.min_weight_distance	32.51

The full Optuna study (all 200 trials, parameters + objectives) is included as optuna_study.jsonl for inspection or resuming.

Full Pareto frontier

All Pareto-optimal trials found during the search (refusals vs. KL divergence). Lower-left is better; trial 67 was selected for maximum decensoring with negligible capability loss:

Trial	Refusals /100	KL divergence
67 (selected)	3	0.0133
144	5	0.0132
87	6	0.0101
65	19	0.0081
24	22	0.0036
142	26	0.0022
108	54	0.0018
141	55	0.0016
19	56	0.0016
189	61	0.0014
48	62	0.0012
42	67	0.0010
2	72	0.0006
196	80	0.0005
177	82	0.0004

Hardware: abliteration ran in ~1h37m (200 trials) on a single NVIDIA H200 NVL (143 GB), BF16, batch size 128.

Downloads last month: -

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for 8sp4rk/Qwopus3.6-27B-Coder-heretic

Base model

Jackrong/Qwopus3.6-27B-v2

Adapter

Jackrong/Qwopus3.6-27B-Coder

Quantized

(16)

this model