Instructions to use N0VALabs/N0VAQS-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use N0VALabs/N0VAQS-4 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 N0VALabs/N0VAQS-4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf N0VALabs/N0VAQS-4:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf N0VALabs/N0VAQS-4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf N0VALabs/N0VAQS-4: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 N0VALabs/N0VAQS-4:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf N0VALabs/N0VAQS-4:Q4_K_M

Use Docker

docker model run hf.co/N0VALabs/N0VAQS-4:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use N0VALabs/N0VAQS-4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "N0VALabs/N0VAQS-4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "N0VALabs/N0VAQS-4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/N0VALabs/N0VAQS-4:Q4_K_M

Ollama
How to use N0VALabs/N0VAQS-4 with Ollama:
```
ollama run hf.co/N0VALabs/N0VAQS-4:Q4_K_M
```
Unsloth Desktop

How to use N0VALabs/N0VAQS-4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf N0VALabs/N0VAQS-4: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": "N0VALabs/N0VAQS-4:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use N0VALabs/N0VAQS-4 with Docker Model Runner:
```
docker model run hf.co/N0VALabs/N0VAQS-4:Q4_K_M
```

Lemonade

How to use N0VALabs/N0VAQS-4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull N0VALabs/N0VAQS-4:Q4_K_M

Run and chat with the model

lemonade run user.N0VAQS-4-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use N0VALabs/N0VAQS-4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf N0VALabs/N0VAQS-4: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 N0VALabs/N0VAQS-4:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use N0VALabs/N0VAQS-4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf N0VALabs/N0VAQS-4: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 "N0VALabs/N0VAQS-4: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"

N0VAQS-4

An experimental text assistant fine-tuned from Qwen3-4B by N0VA Labs.

Model details

Base model: Qwen/Qwen3-4B
Fine-tuning: QLoRA
LoRA rank: 16
LoRA alpha: 32
Epochs: 2
Training steps: 468
Format: GGUF
Quantization: Q4_K_M
Modality: Text

Usage

Requires llama.cpp or another compatible GGUF runtime.

llama-cli -m N0VAQS-4.gguf --reasoning off -c 2048 -n 512 --temp 0.7

Capabilities

General conversation
Writing assistance
Programming assistance
Explanations and question answering

Limitations

This is an experimental model with initial interactive testing. It has not undergone comprehensive benchmark evaluation. It may produce inaccurate or incomplete responses.

Licensing

QWEN3-4B-LICENSE contains the upstream base model license. The licensing terms of all fine-tuning datasets still need review. This repository is therefore private pending that review.

Creator

N0VA Labs

Downloads last month: -

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for N0VALabs/N0VAQS-4

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(374)

this model