Instructions to use Andycurrent/Mistral-7B-Uncensored-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Andycurrent/Mistral-7B-Uncensored-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Andycurrent/Mistral-7B-Uncensored-GGUF",
	filename="mistral-7b-uncensored_F16.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 Andycurrent/Mistral-7B-Uncensored-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Andycurrent/Mistral-7B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Andycurrent/Mistral-7B-Uncensored-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 Andycurrent/Mistral-7B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Andycurrent/Mistral-7B-Uncensored-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/Mistral-7B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Andycurrent/Mistral-7B-Uncensored-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/Mistral-7B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Andycurrent/Mistral-7B-Uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Andycurrent/Mistral-7B-Uncensored-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Andycurrent/Mistral-7B-Uncensored-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Andycurrent/Mistral-7B-Uncensored-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/Mistral-7B-Uncensored-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Andycurrent/Mistral-7B-Uncensored-GGUF:Q4_K_M

Ollama
How to use Andycurrent/Mistral-7B-Uncensored-GGUF with Ollama:
```
ollama run hf.co/Andycurrent/Mistral-7B-Uncensored-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Andycurrent/Mistral-7B-Uncensored-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 Andycurrent/Mistral-7B-Uncensored-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 Andycurrent/Mistral-7B-Uncensored-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Andycurrent/Mistral-7B-Uncensored-GGUF to start chatting

Docker Model Runner
How to use Andycurrent/Mistral-7B-Uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/Andycurrent/Mistral-7B-Uncensored-GGUF:Q4_K_M
```

Lemonade

How to use Andycurrent/Mistral-7B-Uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Andycurrent/Mistral-7B-Uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-7B-Uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Mistral-7B-Uncensored – Lightweight Instruction Model

This repository provides the Mistral-7B-Uncensored model — a 7-billion-parameter conversational system designed for users who need responsive behavior with minimal automated filtering. Ideal for experimentation, offline usage, and custom alignment work.

Model Overview

Model Name: Mistral-7B-Uncensored
Base Architecture: Mistral 7B Transformer
Developer / Maintainer: luvGPT
Training Type: Instruction-oriented fine-tuning
License: Apache 2.0
Intended Use: High-control conversational model for private workflows

Model Purpose

This variant focuses on delivering direct, adaptable responses rather than enforcing heavy policy constraints. It is intended for advanced users, researchers, and self-hosted environments who want to experiment with alignment behavior and prompt specialization. The design emphasizes flexibility, predictable structure during long dialogues, and support for workflows requiring thoughtful reasoning rather than rigid safety layers. Reference formatting inspiration from

Conversation Formatting

The model operates effectively using a dialogue format similar to many Chat-style templates:

<|system|>
System instructions here
<|user|>
User prompt
<|assistant|>

Capabilities

Tuned for instruction-following and productive dialogue
Reduced filtering to support research and customization
Handles contextual reasoning and multi-step tasks
Strong performance on creative writing, utility prompts, and open-ended discussion
Designed for local inference, CPU-friendly runtimes, and quantized deployment
Stable behavior over extended conversations

Suggested Applications

Local assistant usage : general chat, idea development
Developer workflows : code help, debugging, technical explanation
Research environments : prompt engineering, alignment studies
Offline deployments : privacy-sensitive or air-gapped environments
Creative experimentation : storytelling, prototyping characters

Notes & Considerations

The model is not a safety-filtered assistant; responsibility for usage rests with the operator.
Best suited for experienced users familiar with model governance and local deployment practices.

Acknowledgements

Thanks to the Mistral developers and the open-model community for ecosystem support enabling accessible experimentation, as well as contributors who help evaluate and improve lightweight instruction models.

Downloads last month: 1,060

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Andycurrent/Mistral-7B-Uncensored-GGUF

Base model

luvGPT/mistral-7b-uncensored

Quantized

(8)

this model

Collection including Andycurrent/Mistral-7B-Uncensored-GGUF

UNCENSORED MODELS

Collection

14 items • Updated 1 day ago • 17