Instructions to use Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF 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 Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Andycurrent/gemma-3-4b-it-uncensored-v2-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 Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Andycurrent/gemma-3-4b-it-uncensored-v2-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 Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M

Ollama
How to use Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF with Ollama:
```
ollama run hf.co/Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M
```

Lemonade

How to use Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-3-4b-it-uncensored-v2-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Gemma-3-4B-IT-Uncensored-v2

This repository contains Quantized versions of Gemma 3 4B IT Uncensored v2, an instruction-tuned 4B parameter language model designed for users who want a highly responsive, minimally restricted assistant suitable for local, offline, or private deployments. The model is optimized for direct interaction, reasoning, creative tasks, and experimentation, while preserving the efficiency and accessibility of a smaller parameter count.

Model Overview

Model Name: Gemma_3_4B_IT_Uncensored_v2
Base Architecture: Gemma 3 (4B parameters)
License: Inherits the license terms of the original Gemma 3 model
Intended Use: Local or private deployments where users want greater control over alignment, filtering behavior, and conversational tone

What Is Gemma 3 4B IT Uncensored v2?

Gemma-3-4B-IT-Uncensored-v2 is a lightly-aligned, instruction-following model focused on:

User-directed alignment
Reduced artificial guardrails
High responsiveness and clarity
Strong reasoning and step-by-step task handling
Efficient inference on consumer hardware

This version (v2) refines response quality, instruction adherence, and conversational stability compared to earlier releases, making it suitable for both casual and advanced users.

Chat Template & Conversation Format

The model follows a Gemma-style instruction format, typically structured as:

<start_of_turn>user
Your prompt here
<end_of_turn>
<start_of_turn>model

Using the correct chat template is strongly recommended for optimal instruction-following and response quality.

Key Features & Capabilities

Instruction-tuned for clear, concise, and user-aligned responses
Uncensored behavioral tuning for research and experimentation
Effective at conversational, creative, and reasoning tasks
Supports multi-step reasoning and structured answers
Optimized for local inference (CPU and GPU friendly)
Stable output across longer conversations
Suitable for alignment research and prompt engineering

Intended Use Cases

Local assistants – personal chatbots, productivity tools, role-play systems
Coding support – explanations, examples, lightweight debugging
Reasoning tasks – logical breakdowns, step-by-step problem solving
Creative writing – stories, dialogue, brainstorming
Experimentation – uncensored model behavior, alignment testing
Offline / private use – scenarios requiring data locality and user control

Hardware & Performance Notes

With only 4B parameters, this model is well-suited for:

Consumer GPUs
Quantized CPU inference
Embedded or low-resource environments

It offers a strong balance between performance, responsiveness, and efficiency.

Disclaimer

This model is uncensored and designed for research, experimentation, and user-controlled environments. Outputs may include content that would normally be filtered in more restrictive models. Users are responsible for ensuring compliance with applicable laws, policies, and ethical guidelines when deploying or using this model.

Acknowledgements

Special thanks to:

The creators and maintainers of the Gemma 3 architecture
The open-source community supporting training, fine-tuning, quantization, and deployment tools

Downloads last month: 1,089

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF

Base model

braindao/gemma-3-4b-it-uncensored-v2

Quantized

(3)

this model

Collection including Andycurrent/gemma-3-4b-it-uncensored-v2-GGUF

UNCENSORED MODELS

Collection

14 items • Updated Jun 9 • 32