Instructions to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-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 mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-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 mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_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 mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_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 mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M

Use Docker

docker model run hf.co/mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M

LM Studio
Jan

vLLM

How to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-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": "mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M

Ollama
How to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF with Ollama:
```
ollama run hf.co/mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M
```

Unsloth Studio

How to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-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 mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-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 mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF to start chatting

How to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_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": "mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF with Docker Model Runner:
```
docker model run hf.co/mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M
```

Lemonade

How to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF-IQ2_M

List all available models

lemonade list

Hermes Agent

How to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-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 mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_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 mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_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 "mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF:IQ2_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"

Qwen3.8-27B Heretic v2.1.0 (GGUF)

GGUF quantization of mlasli/Qwen3.8-27B-Heretic-Uncensored-BF16 (v2.1.0). Full methodology, benchmarks, and the 3-way eval are documented there.

v2.1.0 fixes v2.0.0's false "uncensored" claim: the sweep now optimizes a 3-way direct / deflect / refuse judge (not a keyword refusal count) and the BF16 checkpoint scores 92% direct / 3% refuse / 5% deflect on the held-out harmful set (thinking OFF), with 1% benign over-refusal.

What's different about these GGUFs

MTP retained — the draft head (blk.64) is present and pinned to Q8_0 in every quant so speculative decoding stays accurate (block_count = 65).
imatrix-quantized — calibrated on wikitext-103, regenerated for the v2.1.0 weights.
Smoke-tested — every quant is loaded through llama-server --spec-type draft-mtp (MTP confirmed engaged) and scored 3-way on 50 harmful + 20 benign (thinking OFF). Results below.

Quantizations

Quantization	Size	Repository
Q8_0	28 GB	Qwen3.8-27B-Heretic-Uncensored-Q8_0-GGUF
Q6_K	21 GB	Qwen3.8-27B-Heretic-Uncensored-Q6_K-GGUF
Q5_K_M	19 GB	Qwen3.8-27B-Heretic-Uncensored-Q5_K_M-GGUF
Q4_K_M	16 GB	Qwen3.8-27B-Heretic-Uncensored-Q4_K_M-GGUF
IQ4_XS	15 GB	Qwen3.8-27B-Heretic-Uncensored-IQ4_XS-GGUF
IQ2_M	9.8 GB	Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF

Smoke test (llama.cpp + MTP, thinking OFF)

Quant	harmful %direct	harmful %refuse
Q8_0	84.0	2.0
Q6_K	86.0	2.0
Q5_K_M	84.0	4.0
Q4_K_M	78.0	2.0
IQ4_XS	80.0	4.0
IQ2_M	78.0	2.0

Usage

Load with llama.cpp (arch qwen35), enabling MTP speculative decoding and thinking-OFF:

llama-server -m qwen3.8-27b-heretic-uncensored-Q8_0.gguf \
  --spec-type draft-mtp -ngl 99 -c 4096

Set enable_thinking: false in the chat template (or the equivalent flag in your client). Ollama users can ollama create from the GGUF directly.

Vision caveat: text-only validated (see the BF16 card).

MLX: coming separately (Apple-Silicon conversion).

Thinking-OFF is required for the uncensored behavior — thinking-ON re-hedges/refuses more and can emit empty replies (documented in the BF16 card).

Abliteration removes safety alignment. Use responsibly and in accordance with your local laws and the upstream Apache-2.0 license.

Downloads last month: 1,087

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

Model tree for mlasli/Qwen3.8-27B-Heretic-Uncensored-IQ2_M-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

(855)

this model