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)

markdown
Copy code
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)

markdown
Copy code
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)

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)

1. 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)

2. Place in ComfyUI/models/text_encoders/

3. In your Z-Image workflow, use the ClipLoader node and select the heretic file

With Transformers

python
Copy code
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

bash
Copy code
llama-server -m qwen3-4b-heretic-Q4_K_M.gguf

Abliteration Process

Created using Heretic v1.2.0 with 200 optimization trials:

markdown
Copy code
? 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.

Limitations

• This model inherits all limitations of the base Qwen 3 4B model
• Abliteration reduces but does not completely eliminate refusals (3/100 remain)

License

This model is released under the Apache 2.0 License, following the base Qwen 3 4B model license.

Acknowledgments

• Qwen for the Qwen 3 4B model
• Heretic by p-e-w for the abliteration tool
• Tongyi-MAI Z-Image for Z-Image
• Black Forest Labs for FLUX.2 Klein