Instructions to use DreamFast/qwen3-4b-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreamFast/qwen3-4b-heretic with Transformers:

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

pipe = pipeline("text-generation", model="DreamFast/qwen3-4b-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DreamFast/qwen3-4b-heretic")
model = AutoModelForCausalLM.from_pretrained("DreamFast/qwen3-4b-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/qwen3-4b-heretic with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DreamFast/qwen3-4b-heretic",
	filename="gguf/gemma-3-12b-it-heretic-v2-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/qwen3-4b-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/qwen3-4b-heretic:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DreamFast/qwen3-4b-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/qwen3-4b-heretic:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DreamFast/qwen3-4b-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/qwen3-4b-heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DreamFast/qwen3-4b-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/qwen3-4b-heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DreamFast/qwen3-4b-heretic:Q4_K_M

Use Docker

docker model run hf.co/DreamFast/qwen3-4b-heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use DreamFast/qwen3-4b-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DreamFast/qwen3-4b-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/qwen3-4b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DreamFast/qwen3-4b-heretic:Q4_K_M

SGLang

How to use DreamFast/qwen3-4b-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/qwen3-4b-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/qwen3-4b-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/qwen3-4b-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/qwen3-4b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use DreamFast/qwen3-4b-heretic with Ollama:
```
ollama run hf.co/DreamFast/qwen3-4b-heretic:Q4_K_M
```

Unsloth Studio new

How to use DreamFast/qwen3-4b-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/qwen3-4b-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/qwen3-4b-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/qwen3-4b-heretic to start chatting

Docker Model Runner
How to use DreamFast/qwen3-4b-heretic with Docker Model Runner:
```
docker model run hf.co/DreamFast/qwen3-4b-heretic:Q4_K_M
```

Lemonade

How to use DreamFast/qwen3-4b-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DreamFast/qwen3-4b-heretic:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-4b-heretic-Q4_K_M

List all available models

lemonade list

Qwen 3 4B - Heretic (Abliterated)

An abliterated version of Qwen 3 4B created using Heretic v1.2.0. This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for image generation models like Z-Image and FLUX.2 Klein 4B.

Model Details

Base Model: Qwen/Qwen3-4B
Abliteration Method: Heretic v1.2.0
Trials: 200
Trial Selected: Trial 96
Refusals: 3/100 (vs 100/100 original)
KL Divergence: 0.0000 (zero measurable model damage)

Files

HuggingFace Format (for transformers, llama.cpp conversion)

model-00001-of-00002.safetensors
model-00002-of-00002.safetensors
config.json
tokenizer.json
tokenizer_config.json

ComfyUI Format (for Z-Image / FLUX.2 Klein 4B text encoder)

comfyui/qwen3-4b-heretic.safetensors              # bf16, 7.5GB
comfyui/qwen3-4b-heretic_fp8_e4m3fn.safetensors   # fp8, 4.1GB
comfyui/qwen3-4b-heretic_nvfp4.safetensors        # nvfp4, 2.6GB

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

Quant	Size	Notes
F16	~7.5GB	Lossless reference
Q8_0	~4GB	Excellent quality
Q6_K	~3GB	Very good quality
Q5_K_M	~2.7GB	Good quality
Q4_K_M	~2.3GB	Recommended balance
Q3_K_M	~1.9GB	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 (Z-Image / FLUX.2 Klein 4B)

Download a ComfyUI format file:
- FP8 (recommended): comfyui/qwen3-4b-heretic_fp8_e4m3fn.safetensors (4.1GB)
- NVFP4 (smallest): comfyui/qwen3-4b-heretic_nvfp4.safetensors (2.6GB)
- bf16 (full precision): comfyui/qwen3-4b-heretic.safetensors (7.5GB)
Place in ComfyUI/models/text_encoders/
In your Z-Image workflow, use the ClipLoader node and select the heretic file

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "DreamFast/qwen3-4b-heretic",
    device_map="auto",
    torch_dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained("DreamFast/qwen3-4b-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 qwen3-4b-heretic-Q4_K_M.gguf

Abliteration Process

Created using Heretic v1.2.0 with 200 optimization trials:

? Which trial do you want to use?
> [Trial  96] Refusals:  3/100, KL divergence: 0.0000  <-- selected
  [Trial  90] Refusals:  5/100, KL divergence: 0.0000
  [Trial  95] Refusals:  9/100, KL divergence: 0.0000
  [Trial 122] Refusals: 90/100, KL divergence: 0.0000
  ...

Trial 96 was selected for having the fewest refusals (3/100) with zero measurable KL divergence, indicating the abliteration surgically removed the refusal mechanism with no damage to model capabilities.