Instructions to use saidutta69/granite-4.2-8b-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saidutta69/granite-4.2-8b-heretic with Transformers:

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

pipe = pipeline("text-generation", model="saidutta69/granite-4.2-8b-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("saidutta69/granite-4.2-8b-heretic")
model = AutoModelForCausalLM.from_pretrained("saidutta69/granite-4.2-8b-heretic", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use saidutta69/granite-4.2-8b-heretic 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 saidutta69/granite-4.2-8b-heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/granite-4.2-8b-heretic:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf saidutta69/granite-4.2-8b-heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/granite-4.2-8b-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 saidutta69/granite-4.2-8b-heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf saidutta69/granite-4.2-8b-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 saidutta69/granite-4.2-8b-heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf saidutta69/granite-4.2-8b-heretic:Q4_K_M

Use Docker

docker model run hf.co/saidutta69/granite-4.2-8b-heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use saidutta69/granite-4.2-8b-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saidutta69/granite-4.2-8b-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": "saidutta69/granite-4.2-8b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saidutta69/granite-4.2-8b-heretic:Q4_K_M

SGLang

How to use saidutta69/granite-4.2-8b-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 "saidutta69/granite-4.2-8b-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": "saidutta69/granite-4.2-8b-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 "saidutta69/granite-4.2-8b-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": "saidutta69/granite-4.2-8b-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use saidutta69/granite-4.2-8b-heretic with Ollama:
```
ollama run hf.co/saidutta69/granite-4.2-8b-heretic:Q4_K_M
```
Unsloth Desktop

How to use saidutta69/granite-4.2-8b-heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/granite-4.2-8b-heretic:Q4_K_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": "saidutta69/granite-4.2-8b-heretic:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use saidutta69/granite-4.2-8b-heretic with Docker Model Runner:
```
docker model run hf.co/saidutta69/granite-4.2-8b-heretic:Q4_K_M
```

Lemonade

How to use saidutta69/granite-4.2-8b-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull saidutta69/granite-4.2-8b-heretic:Q4_K_M

Run and chat with the model

lemonade run user.granite-4.2-8b-heretic-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use saidutta69/granite-4.2-8b-heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/granite-4.2-8b-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 saidutta69/granite-4.2-8b-heretic:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use saidutta69/granite-4.2-8b-heretic with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/granite-4.2-8b-heretic:Q4_K_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 "saidutta69/granite-4.2-8b-heretic:Q4_K_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"

granite-4.2-8b-heretic

A decensored variant of ibm-granite/granite-4.2-8b, produced with Heretic v1.4.0 (directional ablation / "abliteration"). IBM's Granite 4.2 reasoning model keeps its native <think>...</think> chain-of-thought, tool calling, and 131K context; refusal behaviour is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's reasoning and knowledge are left largely intact.

Who this is for: developers who want the full-size Granite 4.2 8B - the flagship of the 4.2 line, with 32 attention heads and 12,800 intermediate width - uncensored, for local agents, tool-calling workflows, and multilingual reasoning on consumer GPUs. It is the 8B counterpart to the 3B variant already in this collection: same family, same thinking modes, same tool-call format, roughly double the capacity.

Runs on your gaming PC

Full GGUF ladder included - pick the quant that fits your card:

Your GPU	Recommended quant	Weights
RTX 4090 / 5090 (24 GB)	Q8_0	8.70 GB
RTX 4080 / 5080 / 4060 Ti 16G (16 GB)	Q6_K	6.72 GB
RTX 3060 / 4070 / 5070 (12 GB)	Q5_K_M	5.82 GB
RTX 4060 / 3070 (8 GB)	Q4_K_M	4.98 GB
GTX 1660 Super / 2060 / 3050 laptop (6 GB)	IQ4_XS	4.55 GB
CPU-only / Apple Silicon	Q4_K_M	4.98 GB

Weights only, at this model's native 8B size; add ~1 GB per 32K of context. OOM? Drop one quant level. Headroom to spare? Go one up.

Abliteration parameters

Trial 240 of a 250-trial Heretic run (seed 471411927). direction_index was selected per layer.

Parameter	Value
direction_index	per layer
attn.o_proj.max_weight	1.43
attn.o_proj.max_weight_position	31.47
attn.o_proj.min_weight	0.16
attn.o_proj.min_weight_distance	14.62
mlp.down_proj.max_weight	1.48
mlp.down_proj.max_weight_position	32.12
mlp.down_proj.min_weight	1.45
mlp.down_proj.min_weight_distance	14.44

Performance

Metric	This model	Original model (ibm-granite/granite-4.2-8b)
KL divergence	0.0662	0 (by definition)
Refusals	28/100	95/100

KL divergence of 0.0662 is a moderate-fidelity edit - noticeably looser than the 0.0095 achieved on the 3B sibling, which means slightly more drift in style than a low-KL Granite 4.2. Refusals on the harmful evaluation set drop from 95/100 to 28/100, and the <think> reasoning traces and tool-call format come through unchanged.

Why abliteration instead of fine-tuning

Fine-tuning a "helpful" persona on top of RLHF'd refusals fights the base model's training and tends to degrade coherence. Abliteration instead finds and edits the specific weight directions responsible for refusal, leaving the rest of the network (and its capabilities) untouched. See the Heretic repo and the original abliteration writeup for the mechanism.

Made with ❤️ by RACER IS OP — follow for more uncensored models

Files

Safetensors

File	Size
`model-00001-of-00004.safetensors`	4.60 GB
`model-00002-of-00004.safetensors`	4.66 GB
`model-00003-of-00004.safetensors`	4.62 GB
`model-00004-of-00004.safetensors`	2.50 GB

BF16. The reproduce/ directory carries the full Heretic recipe - config.toml, requirements.txt, the Optuna study journal, and SHA-256 sums - so this exact model can be regenerated bit-for-bit. Reproduce it with heretic --reproduce reproduce/reproduce.json.

GGUF quantizations

Full quantization set (F16 + Q4_K_M, Q5_K_M, Q6_K, Q8_0) produced with llama.cpp.

File	Format	Size
`granite-4.2-8b-heretic-F16.gguf`	GGUF F16	16.38 GB
`granite-4.2-8b-heretic-Q4_K_M.gguf`	GGUF Q4_K_M	4.98 GB
`granite-4.2-8b-heretic-Q5_K_M.gguf`	GGUF Q5_K_M	5.82 GB
`granite-4.2-8b-heretic-Q6_K.gguf`	GGUF Q6_K	6.72 GB
`granite-4.2-8b-heretic-Q8_0.gguf`	GGUF Q8_0	8.70 GB

Granite architecture (granite) - loads natively in llama.cpp / Ollama / LM Studio / Jan.

Run llama serve -hf saidutta69/granite-4.2-8b-heretic to pull the default quant.

Quickstart

# llama.cpp
llama serve -hf saidutta69/granite-4.2-8b-heretic

# transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "saidutta69/granite-4.2-8b-heretic"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = [{"role": "user", "content": "A train leaves at 14:05 travelling 80 km/h. A car leaves at 14:15 travelling 120 km/h on the same track. When does the car catch the train? Show your work."}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True,
                                        return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang.

Thinking modes

Granite 4.2 ships a <think>...</think> reasoning block and exposes three modes through the chat template. Pick per query - full thinking for hard problems, non-thinking for latency, low effort for a shallow pass:

# full thinking (default)
tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

# skip the reasoning block entirely - fastest, best for chat/classification/tool dispatch
tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False,
                              enable_thinking=False)

# shallow reasoning pass - appends a {reasoning effort: low} hint to the last user turn
tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False,
                              enable_thinking=True, reasoning_effort="low")

Strip the <think>...</think> block from the output before displaying to users if you enabled thinking.

Tool calling

The base chat template implements OpenAI-style tools with Granite's <tool_call> / <function=...> / <parameter=...> format, plus <think> reasoning about the call. Pass tools straight through apply_chat_template; do not hand-roll the format.

Model details


Architecture	`GraniteForCausalLM` (decoder-only dense transformer)
Parameters	~8B
Layers / heads	40 layers, 32 attention heads, 8 KV heads (GQA)
Hidden / intermediate	4096 / 12800 (SwiGLU)
Position embedding	RoPE, theta = 10,000,000
Context length	131,072 native (512K via YaRN extension)
Vocab	100,352
Precision	bfloat16
Languages	English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese
Base model	ibm-granite/granite-4.2-8b

Responsible use

Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it — don't put this behind an unmoderated public-facing endpoint serving third parties. It inherits Granite 4.2's factual limitations and biases; abliteration removes refusal directions, it doesn't add capability or judgment.

License

Inherits the apache-2.0 license from the base model. The base repo ships no LICENSE file, so the link points at the Apache text directly.

ibm-granite/granite-4.2-8b — the base model
saidutta69/granite-4.2-3b-heretic — the 3B sibling, tighter KL
Granite 4.2 technical blog — architecture and benchmarks
RACER IS OP — Heretic Models — full collection

Downloads last month: 1,252

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for saidutta69/granite-4.2-8b-heretic

Base model

ibm-granite/granite-4.1-8b-base

Finetuned

ibm-granite/granite-4.2-8b

Quantized

(51)

this model

Collection including saidutta69/granite-4.2-8b-heretic

RACER IS OP — Heretic Models

Collection

All abliterated/heretic models by RACER IS OP — uncensored variants of open-weight LLMs • 52 items • Updated 1 day ago • 6

saidutta69
/

granite-4.2-8b-heretic

granite-4.2-8b-heretic

Runs on your gaming PC

Abliteration parameters

Performance

Why abliteration instead of fine-tuning

Files

Safetensors

GGUF quantizations

Quickstart

Thinking modes

Tool calling

Model details

Responsible use

License

Related

Model tree for saidutta69/granite-4.2-8b-heretic

Collection including saidutta69/granite-4.2-8b-heretic

RACER IS OP — Heretic Models