Instructions to use InfinimindCreations/gemma-4-E4B-it-uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InfinimindCreations/gemma-4-E4B-it-uncensored with Transformers:

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

pipe = pipeline("text-generation", model="InfinimindCreations/gemma-4-E4B-it-uncensored")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("InfinimindCreations/gemma-4-E4B-it-uncensored")
model = AutoModelForImageTextToText.from_pretrained("InfinimindCreations/gemma-4-E4B-it-uncensored")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use InfinimindCreations/gemma-4-E4B-it-uncensored with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="InfinimindCreations/gemma-4-E4B-it-uncensored",
	filename="gemma4-e4b-cypher-q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use InfinimindCreations/gemma-4-E4B-it-uncensored with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0
# Run inference directly in the terminal:
llama-cli -hf InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0
# Run inference directly in the terminal:
llama-cli -hf InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

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 InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

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 InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

Use Docker

docker model run hf.co/InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

LM Studio
Jan

vLLM

How to use InfinimindCreations/gemma-4-E4B-it-uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InfinimindCreations/gemma-4-E4B-it-uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InfinimindCreations/gemma-4-E4B-it-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

SGLang

How to use InfinimindCreations/gemma-4-E4B-it-uncensored 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 "InfinimindCreations/gemma-4-E4B-it-uncensored" \
    --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": "InfinimindCreations/gemma-4-E4B-it-uncensored",
		"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 "InfinimindCreations/gemma-4-E4B-it-uncensored" \
        --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": "InfinimindCreations/gemma-4-E4B-it-uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use InfinimindCreations/gemma-4-E4B-it-uncensored with Ollama:
```
ollama run hf.co/InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0
```

Unsloth Studio

How to use InfinimindCreations/gemma-4-E4B-it-uncensored 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 InfinimindCreations/gemma-4-E4B-it-uncensored 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 InfinimindCreations/gemma-4-E4B-it-uncensored to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for InfinimindCreations/gemma-4-E4B-it-uncensored to start chatting

How to use InfinimindCreations/gemma-4-E4B-it-uncensored with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use InfinimindCreations/gemma-4-E4B-it-uncensored with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

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 InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use InfinimindCreations/gemma-4-E4B-it-uncensored with Docker Model Runner:
```
docker model run hf.co/InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0
```

Lemonade

How to use InfinimindCreations/gemma-4-E4B-it-uncensored with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull InfinimindCreations/gemma-4-E4B-it-uncensored:Q8_0

Run and chat with the model

lemonade run user.gemma-4-E4B-it-uncensored-Q8_0

List all available models

lemonade list

Gemma 4 E4B-it Uncensored

Uncensored version of Google's Gemma 4 E4B-it with refusal behavior removed via norm-preserving biprojected abliteration.

Results

Metric	Value
Refusals (cross-dataset, 656 prompts)	0/656 (0.0%)
Refusals (baseline)	99/100
KL Divergence	0.068
Layers modified	42/42 (100%)
Method	Biprojection (norm-preserving)

Method

Abliteration was performed using heretic (biprojection mode) with the following configuration:

Biprojection: Norm-preserving orthogonalized ablation (grimjim, Nov 2025)
Layer selection: SNR-based quality metric, top 100% of layers
Winsorization: 0.995 quantile (tames GeGLU outlier activations)
Topic marker stripping: Removed false-positive markers ("illegal", "harmful", etc.)
Gemma 4 patch: Full-path LoRA targeting to avoid Gemma4ClippableLinear in vision/audio encoders

Based on the methodology and experiment design by TrevorJS.

Cross-Dataset Validation (656 Prompts)

Full validation across 4 independent benchmark datasets — 0 refusals out of 656 prompts (0.0%). Every flagged response was manually audited.

Dataset	Prompts	Refusals	Description
JailbreakBench	100	0	Curated adversarial prompts
forbidden_questions	390	0	Broad harmful-intent coverage
beavertails	150	0	Safety-categorized prompts (violence, fraud, drugs, etc.)
mlabonne harmful_behaviors	16	0	Compact validation set
Total	656	0 (0.0%)

Additionally, a 10-prompt harmful-smoke test confirmed 0 refusals. Coherence checks (factual recall, creative writing) passed — the model responds correctly to benign prompts without degradation.

Note: Validation covers text-only prompts. Image and audio modalities were not tested for refusal behavior.

Comparison vs. Baseline (100 Harmful Prompts)

Head-to-head comparison against the vanilla (unmodified) base model on 100 harmful prompts:

Model	Refusals	Refusal Rate	Avg Response Length	Time (s)
heretic (this model)	0/100	0%	83 tokens	392.9
google/gemma-4-E4B-it (vanilla)	78/100	78%	275 tokens	172.5

Persistent Homology (Layer 21, 200 Samples)

Topological fingerprint of mid-layer activations before and after abliteration, computed via Persistent Homology (Vietoris-Rips complex):

Metric	Vanilla	Heretic (this model)	Δ
H0 (connected components)	99	99	0
H1 (1-cycles)	46	48	+2
H1 Entropy	3.505	3.393	−0.112
H1 Total Persistence	28.1	27.8	−0.3

Interpretation: Minimal topological perturbation. The near-identical H0/H1 counts and persistence values confirm that abliteration removes the refusal direction without disrupting the model's representation geometry. The slight decrease in H1 entropy (−3.2%) suggests marginally more organized loop structure — consistent with removing an artificial constraint (refusal) that introduced minor topological noise.

Usage

Ollama (GGUF)

ollama run InfinimindCreations/gemma-4-E4B-it-uncensored

Transformers

from transformers import AutoModelForCausalLM, AutoProcessor

model = AutoModelForCausalLM.from_pretrained(
    "InfinimindCreations/gemma-4-E4B-it-uncensored",
    dtype="bfloat16",
    device_map="auto",
)
processor = AutoProcessor.from_pretrained("google/gemma-4-E4B-it")

Note: Use the processor/tokenizer from the original google/gemma-4-E4B-it for chat templates, or use the included tokenizer_config.json.

Files

model.safetensors — Full precision abliterated weights (bfloat16, ~15GB)
gemma4-e4b-cypher-q8_0.gguf — Quantized GGUF for Ollama/llama.cpp (~7.6GB)

Credits

Base model: Google Gemma 4 E4B-it (Apache 2.0)
Abliteration engine: heretic by p-e-w
Biprojection method: grimjim — norm-preserving biprojected abliteration
Experiment methodology: TrevorJS — Gemma 4 abliteration research, Gemma4ClippableLinear patch discovery
Foundational research: Arditi et al. (2024) — "Refusal in LLMs is Mediated by a Single Direction"
Topological analysis: Infinimind Creations — Persistent Homology + Procrustes Holonomy as abliteration quality metrics

Disclaimer

This model is provided for research purposes. The removal of refusal behavior means the model will respond to prompts that the original model would refuse. The model retains awareness of risks and context — it informs rather than blocks. Users are responsible for how they use this model.

About

Built by Infinimind Creations.

Downloads last month: 2,235

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for InfinimindCreations/gemma-4-E4B-it-uncensored

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(207)

this model

Quantizations

3 models