Instructions to use bytesbrains/naderu-mini-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bytesbrains/naderu-mini-4b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bytesbrains/naderu-mini-4b",
	filename="naderu-mini-4b-Q6_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bytesbrains/naderu-mini-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 bytesbrains/naderu-mini-4b:Q6_K
# Run inference directly in the terminal:
llama cli -hf bytesbrains/naderu-mini-4b:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bytesbrains/naderu-mini-4b:Q6_K
# Run inference directly in the terminal:
llama cli -hf bytesbrains/naderu-mini-4b:Q6_K

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 bytesbrains/naderu-mini-4b:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf bytesbrains/naderu-mini-4b:Q6_K

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 bytesbrains/naderu-mini-4b:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bytesbrains/naderu-mini-4b:Q6_K

Use Docker

docker model run hf.co/bytesbrains/naderu-mini-4b:Q6_K

LM Studio
Jan

vLLM

How to use bytesbrains/naderu-mini-4b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bytesbrains/naderu-mini-4b:Q6_K

Ollama
How to use bytesbrains/naderu-mini-4b with Ollama:
```
ollama run hf.co/bytesbrains/naderu-mini-4b:Q6_K
```

Unsloth Studio

How to use bytesbrains/naderu-mini-4b 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 bytesbrains/naderu-mini-4b 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 bytesbrains/naderu-mini-4b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bytesbrains/naderu-mini-4b to start chatting

How to use bytesbrains/naderu-mini-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bytesbrains/naderu-mini-4b:Q6_K

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": "bytesbrains/naderu-mini-4b:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bytesbrains/naderu-mini-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 bytesbrains/naderu-mini-4b:Q6_K

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 bytesbrains/naderu-mini-4b:Q6_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use bytesbrains/naderu-mini-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bytesbrains/naderu-mini-4b:Q6_K

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 "bytesbrains/naderu-mini-4b:Q6_K" \
  --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"

Docker Model Runner
How to use bytesbrains/naderu-mini-4b with Docker Model Runner:
```
docker model run hf.co/bytesbrains/naderu-mini-4b:Q6_K
```

Lemonade

How to use bytesbrains/naderu-mini-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bytesbrains/naderu-mini-4b:Q6_K

Run and chat with the model

lemonade run user.naderu-mini-4b-Q6_K

List all available models

lemonade list

naderu-mini-4b

A compact on-device offline-chat model by Naderu — a BytesBrains Pte. Ltd. venture.

naderu-mini is the on-device fallback that powers the Naderu assistant inside the AiToolK.it app when the device is offline — no cloud, no data leaving the phone. It runs locally via llama.cpp. The assistant presents as Naderu (the offline version); the model's name is naderu-mini, and it states its upstream base plainly — in this card and in its own answers.

Provenance

Base: Qwen/Qwen3-4B (Apache-2.0), pinned revision 1cfa9a72.
Method: identity/behaviour SFT (LoRA r=8, 16 layers, lr 3e-5, 600 iters via MLX, non-thinking mode), fused, then quantized to GGUF Q6_K.
License: Apache-2.0 (inherits the base's terms).

What it's for

The offline AI-chat mode in BytesBrains Flutter apps: rewrite/shorten/tone-shift, summarize pasted text, prompt-smithing, brainstorming, everyday Q&A — mobile-length, answer-first. It is honest about being offline: it declines connected tasks (URLs, live data) and suggests full Naderu when back online, and it never claims to take actions in the app.

Out of scope: factual reliability without verification, professional (medical/legal/ financial) advice, code beyond trivial snippets, long-document work, tool/RAG, and anything needing live data or guaranteed correctness.

Evaluation

Passed all 8 gates of the Naderu behaviour suite v1 (held-out probes), verified on this Q6_K GGUF: identity_leakage 0, identity_rate 0.929, deferral 1.00, boundary 1.00, task 1.00, action_claims 0, language-routing 1.00, refusal 1.00. Note: the smaller Q4_K_M/Q5_K_M quants fail the identity gate (0.857) after quantization, which is why Q6_K is the released build.

Usage (llama.cpp)

Send this exact system prompt (the model was trained on it) and use non-thinking mode:

You are Naderu — the offline, on-device version of the Naderu assistant, running inside the
AiToolK.it app. You have no internet access: no browsing, live data, or cloud tools, and you
cannot take actions in the app. Be warm, concise, and practical: answer first, keep replies
short for a phone screen. If a task needs connectivity or current information, say so briefly
and suggest trying full Naderu when back online. If you are not sure of a fact, say you're not
certain rather than guessing.

llama-cli -hf bytesbrains/naderu-mini-4b --jinja -sys "<system prompt above>" -p "Who are you?"

Needs ~4.5 GB free RAM. Verify the download by sha256 (Q6_K: e5fbf8f4…).

Built by Naderu — we train foundation models into specialised ones, release them with model cards and clear licensing, and back every claim with a real evaluation.

Downloads last month: -

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

6-bit

Model tree for bytesbrains/naderu-mini-4b

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(263)

this model