Instructions to use mistralai/Ministral-3-8B-Instruct-2512-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mistralai/Ministral-3-8B-Instruct-2512-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mistralai/Ministral-3-8B-Instruct-2512-GGUF",
	filename="Ministral-3-8B-Instruct-2512-BF16-mmproj.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 mistralai/Ministral-3-8B-Instruct-2512-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mistralai/Ministral-3-8B-Instruct-2512-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 mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mistralai/Ministral-3-8B-Instruct-2512-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 mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mistralai/Ministral-3-8B-Instruct-2512-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 mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mistralai/Ministral-3-8B-Instruct-2512-GGUF with Ollama:
```
ollama run hf.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
```

Unsloth Studio new

How to use mistralai/Ministral-3-8B-Instruct-2512-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 mistralai/Ministral-3-8B-Instruct-2512-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 mistralai/Ministral-3-8B-Instruct-2512-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mistralai/Ministral-3-8B-Instruct-2512-GGUF to start chatting

Pi new

How to use mistralai/Ministral-3-8B-Instruct-2512-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M

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": "mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mistralai/Ministral-3-8B-Instruct-2512-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mistralai/Ministral-3-8B-Instruct-2512-GGUF: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 mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use mistralai/Ministral-3-8B-Instruct-2512-GGUF with Docker Model Runner:
```
docker model run hf.co/mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M
```

Lemonade

How to use mistralai/Ministral-3-8B-Instruct-2512-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ministral-3-8B-Instruct-2512-GGUF-Q4_K_M

List all available models

lemonade list

Ministral 3 8B Instruct 2512 GGUF

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

This model includes different quantization levels of the instruct post-trained version in GGUF, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 8B can even be deployed locally, capable of fitting in 12GB of VRAM in FP8, and less if further quantized.

Learn more in our blog post and paper.

Key Features

Ministral 3 8B consists of two main architectural components:

8.4B Language Model
0.4B Vision Encoder

The Ministral 3 8B Instruct model offers the following capabilities:

Vision: Enables the model to analyze images and provide insights based on visual content, in addition to text.
Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
System Prompt: Maintains strong adherence and support for system prompts.
Agentic: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
Edge-Optimized: Delivers best-in-class performance at a small scale, deployable anywhere.
Apache 2.0 License: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
Large Context Window: Supports a 256k context window.

Recommended Settings

We recommend deploying with the following best practices:

System Prompt: Define a clear environment and use case, including guidance on how to effectively leverage tools in agentic systems.
Sampling Parameters: Use a temperature below 0.1 for daily-driver and production environments ; Higher temperatures may be explored for creative use cases - developers are encouraged to experiment with alternative settings.
Tools: Keep the set of tools well-defined and limit their number to the minimum required for the use case - Avoiding overloading the model with an excessive number of tools.
Vision: When deploying with vision capabilities, we recommend maintaining an aspect ratio close to 1:1 (width-to-height) for images. Avoiding the use of overly thin or wide images - crop them as needed to ensure optimal performance.

License

This model is licensed under the Apache 2.0 License.

You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.