Instructions to use M1n1A1/MiniAI-Quata2-4b-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 M1n1A1/MiniAI-Quata2-4b-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 M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf M1n1A1/MiniAI-Quata2-4b-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 M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use M1n1A1/MiniAI-Quata2-4b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "M1n1A1/MiniAI-Quata2-4b-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": "M1n1A1/MiniAI-Quata2-4b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M

Ollama
How to use M1n1A1/MiniAI-Quata2-4b-GGUF with Ollama:
```
ollama run hf.co/M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M
```
Unsloth Desktop

How to use M1n1A1/MiniAI-Quata2-4b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf M1n1A1/MiniAI-Quata2-4b-GGUF: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": "M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use M1n1A1/MiniAI-Quata2-4b-GGUF with Docker Model Runner:
```
docker model run hf.co/M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M
```

Lemonade

How to use M1n1A1/MiniAI-Quata2-4b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniAI-Quata2-4b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use M1n1A1/MiniAI-Quata2-4b-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf M1n1A1/MiniAI-Quata2-4b-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 M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use M1n1A1/MiniAI-Quata2-4b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf M1n1A1/MiniAI-Quata2-4b-GGUF: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 "M1n1A1/MiniAI-Quata2-4b-GGUF: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"

MiniAI Quata2 (4B) — GGUF

GGUF build of MiniAI Quata2 (4B) for llama.cpp, LM Studio, Ollama and other GGUF runtimes. Benchmarks, training details and the citation are on the main model card.

File	Quant	Size	Use it when
`MiniAI-Quata2-4b-Q4_K_M.gguf`	Q4_K_M	2.5 GB	Default. Fits 4–6 GB GPUs and laptops; this is what Ollama and MiniAI's own server run
`MiniAI-Quata2-4b-Q5_K_M.gguf`	Q5_K_M	2.9 GB	A bit closer to full quality, still small
`MiniAI-Quata2-4b-Q6_K.gguf`	Q6_K	3.3 GB	Near-lossless
`MiniAI-Quata2-4b-Q8_0.gguf`	Q8_0	4.3 GB	Practically identical to the BF16 weights

All files are quantized with llama.cpp from the released BF16 weights. SHA-256:

e53513972034fbaa6420e95fec670106844938a0d07eae265ad5aed0b89bf8f1  MiniAI-Quata2-4b-Q8_0.gguf
a27145dc5becd40db37bc43a73adbabe88af54fef8641de05d570ed584773c63  MiniAI-Quata2-4b-Q6_K.gguf
36c27199355c8641a579c076ab49ff9f85c834d1085770cd9df401619767b29f  MiniAI-Quata2-4b-Q5_K_M.gguf

Run it

# Ollama (recommended: ships the correct hybrid-thinking chat template)
ollama run miniai/quata2:4b

# llama.cpp
llama-cli -hf M1n1A1/MiniAI-Quata2-4b-GGUF:Q4_K_M -cnv   # or :Q5_K_M, :Q6_K, :Q8_0

Thinking is on by default. Add /no_think to a message for a direct answer, or /think to switch it back on. Recommended sampling: temperature 0.6, top_p 0.95, top_k 20 when thinking; 0.7 / 0.8 / 20 without.

Try it in the browser: chat.codeminute.dev · Hosted API: miniai.codeminute.dev

License: Apache 2.0 (base: Qwen3-4B).

Downloads last month: 209

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Model tree for M1n1A1/MiniAI-Quata2-4b-GGUF

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

M1n1A1/MiniAI-Quata2-4b

Quantized

(3)

this model