Instructions to use vinci00/ministral-3-3b-gguf-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use vinci00/ministral-3-3b-gguf-q4 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 vinci00/ministral-3-3b-gguf-q4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vinci00/ministral-3-3b-gguf-q4:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vinci00/ministral-3-3b-gguf-q4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vinci00/ministral-3-3b-gguf-q4: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 vinci00/ministral-3-3b-gguf-q4:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vinci00/ministral-3-3b-gguf-q4: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 vinci00/ministral-3-3b-gguf-q4:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vinci00/ministral-3-3b-gguf-q4:Q4_K_M

Use Docker

docker model run hf.co/vinci00/ministral-3-3b-gguf-q4:Q4_K_M

LM Studio
Jan

vLLM

How to use vinci00/ministral-3-3b-gguf-q4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vinci00/ministral-3-3b-gguf-q4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vinci00/ministral-3-3b-gguf-q4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vinci00/ministral-3-3b-gguf-q4:Q4_K_M

Ollama
How to use vinci00/ministral-3-3b-gguf-q4 with Ollama:
```
ollama run hf.co/vinci00/ministral-3-3b-gguf-q4:Q4_K_M
```
Unsloth Desktop

How to use vinci00/ministral-3-3b-gguf-q4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vinci00/ministral-3-3b-gguf-q4:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "vinci00/ministral-3-3b-gguf-q4:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use vinci00/ministral-3-3b-gguf-q4 with Docker Model Runner:
```
docker model run hf.co/vinci00/ministral-3-3b-gguf-q4:Q4_K_M
```

Lemonade

How to use vinci00/ministral-3-3b-gguf-q4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vinci00/ministral-3-3b-gguf-q4:Q4_K_M

Run and chat with the model

lemonade run user.ministral-3-3b-gguf-q4-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use vinci00/ministral-3-3b-gguf-q4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vinci00/ministral-3-3b-gguf-q4: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 vinci00/ministral-3-3b-gguf-q4:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use vinci00/ministral-3-3b-gguf-q4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vinci00/ministral-3-3b-gguf-q4:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "vinci00/ministral-3-3b-gguf-q4:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Ministral 3 3B Instruct 2512 — GGUF Q4_K_M

This repository contains a community GGUF conversion and Q4_K_M quantization of mistralai/Ministral-3-3B-Instruct-2512-BF16 for Ollama and llama.cpp-compatible runtimes.

This is a text-generation distribution. It is a separate GGUF quantization from the MLX 4-bit artifact; it was created from the same official BF16 checkpoint, not by converting MLX weights back to GGUF.

Files

File	Description
`Ministral-3-3B-Instruct-2512-Q4_K_M.gguf`	2.1 GB GGUF Q4_K_M model
`Modelfile`	Ollama import recipe
`README.md`	This model card

Use with Ollama

Download the GGUF and Modelfile into the same directory, then run:

ollama create ministral-3-3b-mlx -f Modelfile
ollama run ministral-3-3b-mlx

The published model can also be referenced from the Hub using the Ollama Hugging Face integration when supported by the installed Ollama version:

ollama run hf.co/vinci00/ministral-3-3b-gguf-q4

Conversion provenance

The source checkpoint was the official Mistral AI BF16 Safetensors model. The conversion used the current llama.cpp converter and llama-quantize with Q4_K_M. The reproducible MLX conversion notebook, benchmark, and source card are maintained at vinci00/ministral-3-mlx-4bit and in the course repository.

Validation

The same four fixed functional prompts used for the MLX artifact passed when the resulting model was loaded through Ollama on an Apple M4 Mac mini. This is a small smoke test, not a quality, safety, or task benchmark.

Accuracy before and after quantization

BF16 versus GGUF Q4_K_M accuracy has not been measured. The four smoke checks above do not estimate task accuracy or establish parity with BF16.

The source repository now includes benchmark_accuracy.py: a paired GSM8K test evaluation for the MLX unquantized and 4-bit checkpoints, with exact-match scoring, accuracy changes in percentage points, uncertainty intervals, and chart output. Its MLX inference backend does not accept this GGUF artifact or call Ollama.

A valid GGUF comparison still requires evaluating the original unquantized source and Q4_K_M on identical held-out questions, prompts, decoding settings, and scoring, preferably within the same runtime. Record both runtime and precision if comparing across runtimes. Do not copy MLX accuracy numbers into this card: the quantization formats and inference implementations differ. The MLX comparison measured 87/100 for both BF16 and MLX 4-bit on a fixed 100-example GSM8K test sample (2026-09-21, M1 Pro). This is evidence for the MLX artifacts only. No GSM8K accuracy result is claimed for this GGUF/Ollama distribution. See the source repository for raw results and methodology.

Limitations

This GGUF card documents text-only Ollama use; image understanding was not validated in Ollama.
Quantization can change accuracy, calibration, tool use, and refusal behaviour. Validate representative workloads before production use.
The model may produce incorrect, biased, unsafe, or culturally insensitive outputs. Follow the upstream Mistral model card and add application-level safeguards.

License

The upstream checkpoint is released under the Apache 2.0 license. Preserve the upstream attribution and model card when redistributing this derivative.

Downloads last month: 216

GGUF

Model size

3B params

Architecture

mistral3

Hardware compatibility

4-bit

Model tree for vinci00/ministral-3-3b-gguf-q4

Base model

mistralai/Ministral-3-3B-Base-2512

Finetuned

mistralai/Ministral-3-3B-Instruct-2512-BF16

Quantized

(20)

this model