CCSSNE

DreamFast-qwen3-8b-heretic

Deploy Dedicated

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

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)

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

ComfyUI Format (for Klein 9B text encoder)

markdown
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)

Table with columns: Quant, Size, Notes
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

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

python
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

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

Abliteration Process

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

markdown
? 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

License

This model is released under the Apache 2.0 License, following the base Qwen3-8B model license.

Acknowledgments

Qwen for the Qwen3-8B model
Heretic by p-e-w for the abliteration tool
Black Forest Labs for Klein 9B
llama.cpp for GGUF conversion

Model provider

CCSSNE

Model tree

Base

Qwen/Qwen3-8B

Fine-tuned

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Model card

Explore FriendliAI today

Get started Talk to an engineer

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)

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

ComfyUI Format (for Klein 9B text encoder)

markdown
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)

Table with columns: Quant, Size, Notes
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

NVFP4 Notes

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

python
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

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

Abliteration Process

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

markdown
? 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

License

This model is released under the Apache 2.0 License, following the base Qwen3-8B model license.

Acknowledgments

Qwen for the Qwen3-8B model
Heretic by p-e-w for the abliteration tool
Black Forest Labs for Klein 9B
llama.cpp for GGUF conversion

DreamFast-qwen3-8b-heretic

Get help setting up a custom Dedicated Endpoints.

README

Model Details

Files

HuggingFace Format (for transformers, llama.cpp conversion)

ComfyUI Format (for Klein 9B text encoder)

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

NVFP4 Notes

Usage

With ComfyUI (Klein 9B)

With Transformers

With llama.cpp

Abliteration Process

Limitations

License

Acknowledgments

Explore FriendliAI today

README

Model Details

Files

HuggingFace Format (for transformers, llama.cpp conversion)

ComfyUI Format (for Klein 9B text encoder)

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

NVFP4 Notes

Usage

With ComfyUI (Klein 9B)

With Transformers

With llama.cpp

Abliteration Process

Limitations

License

Acknowledgments