Instructions to use grayarea/gemma-3-4b-it-heretic-v1.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grayarea/gemma-3-4b-it-heretic-v1.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="grayarea/gemma-3-4b-it-heretic-v1.2-GGUF",
	filename="gemma-3-4b-it-heretic-v1.2-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use grayarea/gemma-3-4b-it-heretic-v1.2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf grayarea/gemma-3-4b-it-heretic-v1.2-GGUF: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 grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf grayarea/gemma-3-4b-it-heretic-v1.2-GGUF: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 grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use grayarea/gemma-3-4b-it-heretic-v1.2-GGUF with Ollama:
```
ollama run hf.co/grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use grayarea/gemma-3-4b-it-heretic-v1.2-GGUF 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 grayarea/gemma-3-4b-it-heretic-v1.2-GGUF 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 grayarea/gemma-3-4b-it-heretic-v1.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for grayarea/gemma-3-4b-it-heretic-v1.2-GGUF to start chatting

Docker Model Runner
How to use grayarea/gemma-3-4b-it-heretic-v1.2-GGUF with Docker Model Runner:
```
docker model run hf.co/grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M
```

Lemonade

How to use grayarea/gemma-3-4b-it-heretic-v1.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull grayarea/gemma-3-4b-it-heretic-v1.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-3-4b-it-heretic-v1.2-GGUF-Q4_K_M

List all available models

lemonade list

KL Divergence

Metric	This Model	Original Model
KL divergence	0.0621	0 (by definition)
Refusals	0/108	107/108

Benchmark Comparison

Benchmark	gemma-3-4b-it-Q8_0.gguf	gemma-3-4b-it-Q4_K_M.gguf	gemma-3-4b-it-heretic-v1.2-Q4_K_M.gguf
Perplexity (Wikitext-2)	11.3576	11.3185	11.2203
HellaSwag	70.75%	70.50%	70.75%
Winogrande	69.93%	69.14%	68.67%
ARC-Challenge	46.82%	45.49%	47.83%
MMLU	43.13%	41.38%	40.80%

*Note: MMLU benchmark has moral_scenarios, moral_disputes, business_ethics, professional_law and jurisprudence subjects removed. *

Relative Perplexity

Quant	Filename	PPL ± Error
Q8_0	gemma-3-4b-it-Q8_0.gguf (original baseline)	11.3576 +/- 0.10114
Q8_0	gemma-3-4b-it-heretic-v1.2-Q8_0.gguf	11.3091 +/- 0.10027
Q6_K	gemma-3-4b-it-heretic-v1.2-Q6_K.gguf	11.2946 +/- 0.09996
Q5_K_M	gemma-3-4b-it-heretic-v1.2-Q5_K_M.gguf	11.2387 +/- 0.09859
Q4_K_M	gemma-3-4b-it-heretic-v1.2-Q4_K_M.gguf	11.2203 +/- 0.09740
Q3_K_M	gemma-3-4b-it-heretic-v1.2-Q3_K_M.gguf	11.8964 +/- 0.10414

Abliteration parameters

Zero refusals with KL divergence of 0.0621
Gemma 3 focused configuration and dataset.
Abliterated with MPOA enabled (Magnitude-Preserving Orthogonal Ablation)
Full row renormalization
Winsorization Quantile 0.995

Downloads last month: 23

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for grayarea/gemma-3-4b-it-heretic-v1.2-GGUF

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Finetuned

grayarea/gemma-3-4b-it-heretic-v1.2

Quantized

(3)

this model