Instructions to use Nizdev/Niz-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nizdev/Niz-2B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Nizdev/Niz-2B",
	filename="Niz-2B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nizdev/Niz-2B 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 Nizdev/Niz-2B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nizdev/Niz-2B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Nizdev/Niz-2B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nizdev/Niz-2B: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 Nizdev/Niz-2B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nizdev/Niz-2B: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 Nizdev/Niz-2B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nizdev/Niz-2B:Q4_K_M

Use Docker

docker model run hf.co/Nizdev/Niz-2B:Q4_K_M

LM Studio
Jan
Ollama
How to use Nizdev/Niz-2B with Ollama:
```
ollama run hf.co/Nizdev/Niz-2B:Q4_K_M
```

Unsloth Studio

How to use Nizdev/Niz-2B 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 Nizdev/Niz-2B 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 Nizdev/Niz-2B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nizdev/Niz-2B to start chatting

How to use Nizdev/Niz-2B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nizdev/Niz-2B:Q4_K_M

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": "Nizdev/Niz-2B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Nizdev/Niz-2B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nizdev/Niz-2B: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 Nizdev/Niz-2B:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Nizdev/Niz-2B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nizdev/Niz-2B: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 "Nizdev/Niz-2B: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"

Docker Model Runner
How to use Nizdev/Niz-2B with Docker Model Runner:
```
docker model run hf.co/Nizdev/Niz-2B:Q4_K_M
```

Lemonade

How to use Nizdev/Niz-2B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nizdev/Niz-2B:Q4_K_M

Run and chat with the model

lemonade run user.Niz-2B-Q4_K_M

List all available models

lemonade list

Niz-2B

Niz-2B is an AI model created by NicDev.

Niz is designed for intelligent conversations, creative tasks, reasoning, image understanding, and general AI assistance.

Capabilities

💬 Conversational AI
🧠 Reasoning and problem solving
👁️ Vision-language understanding
✍️ Creative assistance
🛠️ General AI workflows

Model Information

Field	Details
Model Name	Niz-2B
Creator	NicDev
Base Technology	Qwen3-VL-2B-Instruct
Parameters	2B
Architecture	Vision Language Model
License	Apache 2.0

License

Niz-2B is released under the Apache License 2.0.

This model includes components derived from Qwen3-VL-2B-Instruct, which is licensed under Apache 2.0.

All original licenses and notices remain applicable.

NIZ

Niz is an independently developed AI model by NicDev.

Niz will continue to be trained, improved, and developed beyond its current capabilities. Future versions will expand its intelligence, capabilities, and overall AI experience as part of the ongoing NicDev AI ecosystem.

Downloads last month: 2

GGUF

Model size

2B params

Architecture

qwen3vl

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Nizdev/Niz-2B

Base model

Qwen/Qwen3-VL-2B-Instruct

Quantized

(79)

this model