Instructions to use steef68/AIZYBRAIN-NANO-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use steef68/AIZYBRAIN-NANO-4B 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 steef68/AIZYBRAIN-NANO-4B
# Run inference directly in the terminal:
llama cli -hf steef68/AIZYBRAIN-NANO-4B

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf steef68/AIZYBRAIN-NANO-4B
# Run inference directly in the terminal:
llama cli -hf steef68/AIZYBRAIN-NANO-4B

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 steef68/AIZYBRAIN-NANO-4B
# Run inference directly in the terminal:
./llama-cli -hf steef68/AIZYBRAIN-NANO-4B

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 steef68/AIZYBRAIN-NANO-4B
# Run inference directly in the terminal:
./build/bin/llama-cli -hf steef68/AIZYBRAIN-NANO-4B

Use Docker

docker model run hf.co/steef68/AIZYBRAIN-NANO-4B

LM Studio
Jan

vLLM

How to use steef68/AIZYBRAIN-NANO-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "steef68/AIZYBRAIN-NANO-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "steef68/AIZYBRAIN-NANO-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/steef68/AIZYBRAIN-NANO-4B

Ollama
How to use steef68/AIZYBRAIN-NANO-4B with Ollama:
```
ollama run hf.co/steef68/AIZYBRAIN-NANO-4B
```
Unsloth Desktop

How to use steef68/AIZYBRAIN-NANO-4B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steef68/AIZYBRAIN-NANO-4B

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": "steef68/AIZYBRAIN-NANO-4B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use steef68/AIZYBRAIN-NANO-4B with Docker Model Runner:
```
docker model run hf.co/steef68/AIZYBRAIN-NANO-4B
```

Lemonade

How to use steef68/AIZYBRAIN-NANO-4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull steef68/AIZYBRAIN-NANO-4B

Run and chat with the model

lemonade run user.AIZYBRAIN-NANO-4B-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use steef68/AIZYBRAIN-NANO-4B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steef68/AIZYBRAIN-NANO-4B

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 steef68/AIZYBRAIN-NANO-4B

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use steef68/AIZYBRAIN-NANO-4B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steef68/AIZYBRAIN-NANO-4B

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 "steef68/AIZYBRAIN-NANO-4B" \
  --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"

AIZYBRAIN-NANO-4B (GGUF)

AIZYBRAIN-NANO-4B is a high-performance, compact language model in GGUF format, specifically optimized for local inference. It is based on the Qwen3-4B architecture, designed to deliver a perfect balance between reasoning depth and computational efficiency.

🚀 Model Overview

Developer: steef68
Architecture: Qwen3 (Causal Language Model)
Base Model: Qwen3-4B-Instruct
Parameters: 4 Billion
Format: GGUF
Context Window: 32,768 tokens
License: Apache 2.0

✨ Key Features

Reasoning Capabilities: Native support for "Chain-of-Thought" processing using <think> blocks, allowing the model to solve complex logical problems before answering.
Optimized for Edge Devices: Specifically tuned to run smoothly on consumer-grade hardware, including laptops with limited VRAM and CPU-only setups.
Multilingual Expertise: Exceptional performance in French and English, with robust understanding across 20+ additional languages.
High Efficiency: Utilizes Grouped-Query Attention (GQA) for faster inference and lower memory consumption.

🛠 Installation and Usage

For LM Studio / AnythingLLM

Search for steef68/AIZYBRAIN-NANO-4B in the app.
Download the AIZYBRAIN-V2-4B.gguf file.
Select the ChatML or Qwen prompt template.

For Ollama

You can use this model by creating a Modelfile:

FROM ./AIZYBRAIN-V2-4B.gguf
PARAMETER temperature 0.7
TEMPLATE "{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"

Downloads last month: 16

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants