Instructions to use DreamFast/qwen3-8b-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreamFast/qwen3-8b-heretic with Transformers:

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

pipe = pipeline("text-generation", model="DreamFast/qwen3-8b-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DreamFast/qwen3-8b-heretic")
model = AutoModelForCausalLM.from_pretrained("DreamFast/qwen3-8b-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use DreamFast/qwen3-8b-heretic with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DreamFast/qwen3-8b-heretic",
	filename="gguf/qwen3-8b-heretic-Q3_K_M.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use DreamFast/qwen3-8b-heretic with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DreamFast/qwen3-8b-heretic:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DreamFast/qwen3-8b-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 DreamFast/qwen3-8b-heretic:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DreamFast/qwen3-8b-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 DreamFast/qwen3-8b-heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DreamFast/qwen3-8b-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 DreamFast/qwen3-8b-heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DreamFast/qwen3-8b-heretic:Q4_K_M

Use Docker

docker model run hf.co/DreamFast/qwen3-8b-heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use DreamFast/qwen3-8b-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DreamFast/qwen3-8b-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": "DreamFast/qwen3-8b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DreamFast/qwen3-8b-heretic:Q4_K_M

SGLang

How to use DreamFast/qwen3-8b-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 "DreamFast/qwen3-8b-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": "DreamFast/qwen3-8b-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 "DreamFast/qwen3-8b-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": "DreamFast/qwen3-8b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use DreamFast/qwen3-8b-heretic with Ollama:
```
ollama run hf.co/DreamFast/qwen3-8b-heretic:Q4_K_M
```

Unsloth Studio new

How to use DreamFast/qwen3-8b-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 DreamFast/qwen3-8b-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 DreamFast/qwen3-8b-heretic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DreamFast/qwen3-8b-heretic to start chatting

Pi new

How to use DreamFast/qwen3-8b-heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DreamFast/qwen3-8b-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": "DreamFast/qwen3-8b-heretic:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DreamFast/qwen3-8b-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 DreamFast/qwen3-8b-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 DreamFast/qwen3-8b-heretic:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use DreamFast/qwen3-8b-heretic with Docker Model Runner:
```
docker model run hf.co/DreamFast/qwen3-8b-heretic:Q4_K_M
```

Lemonade

How to use DreamFast/qwen3-8b-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DreamFast/qwen3-8b-heretic:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-8b-heretic-Q4_K_M

List all available models

lemonade list

Qwen3 8B - Heretic (Abliterated)

An abliterated version of Qwen's Qwen3-8B created using Heretic v1.2.0 (git master). This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for image generation models like Klein 9B.

You can see the docker, scripts and configurations used to make these files on Heretic Docker Github.

Model Details

Base Model: Qwen/Qwen3-8B
Abliteration Method: Heretic v1.2.0 (git master, commit 19cdf7e)
Trials: 3000
Trial Selected: Trial 2681
Refusals: 13/100 (vs 100/100 original)
KL Divergence: 0.0838 (minimal model damage)

Files

HuggingFace Format (for transformers, llama.cpp conversion)

model.safetensors (~16 GB)
config.json
tokenizer.json
tokenizer_config.json
generation_config.json
chat_template.jinja

ComfyUI Format (for Klein 9B text encoder)

comfyui/qwen3-8b-heretic.safetensors              # bf16, 16GB
comfyui/qwen3-8b-heretic_fp8_e4m3fn.safetensors   # fp8, 8.8GB
comfyui/qwen3-8b-heretic_nvfp4.safetensors        # nvfp4, 6.0GB

GGUF Format (for llama.cpp and ComfyUI-GGUF)

Quant	Size	Notes
F16	16GB	Lossless reference
Q8_0	8.2GB	Excellent quality
Q6_K	6.3GB	Very good quality
Q5_K_M	5.5GB	Good quality
Q5_K_S	5.4GB	Slightly smaller Q5
Q4_K_M	5.0GB	Recommended balance
Q4_K_S	4.8GB	Smaller Q4 variant
Q3_K_M	3.9GB	For low VRAM only

NVFP4 Notes

The NVFP4 (4-bit floating point, E2M1) variants use ComfyUI's native quantization format. They are ~3x smaller than bf16 and load natively in ComfyUI without any plugins. Blackwell GPUs (RTX 5090/5080, SM100+) can use native FP4 tensor cores for best performance, but ComfyUI also supports software dequantization on older GPUs (tested working on RTX 4090).

Usage

With ComfyUI (Klein 9B)

Download a ComfyUI format file:
- FP8 (recommended): comfyui/qwen3-8b-heretic_fp8_e4m3fn.safetensors (8.8GB)
- NVFP4 (smallest): comfyui/qwen3-8b-heretic_nvfp4.safetensors (6.0GB)
- bf16 (full precision): comfyui/qwen3-8b-heretic.safetensors (16GB)
Place in ComfyUI/models/text_encoders/
In your Klein 9B workflow, use the ClipLoader node and select the heretic file

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "DreamFast/qwen3-8b-heretic",
    device_map="auto",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("DreamFast/qwen3-8b-heretic")

prompt = "Describe a dramatic sunset over a cyberpunk city"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

With llama.cpp

llama-server -m qwen3-8b-heretic-Q4_K_M.gguf

Abliteration Process

Created using Heretic v1.2.0 (git master) with 3000 optimization trials:

? Which trial do you want to use?
  [Trial 2732] Refusals: 10/100, KL divergence: 0.1001
> [Trial 2681] Refusals: 13/100, KL divergence: 0.0838  <-- selected
  [Trial 2337] Refusals: 18/100, KL divergence: 0.0643
  [Trial 2419] Refusals: 19/100, KL divergence: 0.0600
  [Trial 2195] Refusals: 21/100, KL divergence: 0.0534
  ...

Trial 2681 was selected for its balance of low refusals (13/100) and reasonable KL divergence (0.0838), indicating minimal model damage while achieving 87% of previously-refused prompts now working.

Limitations

This model inherits all limitations of the base Qwen3-8B model
Abliteration reduces but does not completely eliminate refusals (13/100 remain)
NVFP4 quantization works best on Blackwell GPUs (RTX 5090/5080) with native FP4 tensor cores, but also works on older GPUs via software dequantization