Instructions to use Zorix-official/Zorix-Nano-0.8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zorix-official/Zorix-Nano-0.8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Zorix-official/Zorix-Nano-0.8B-GGUF",
	filename="zorix-nano-0.8b-q5_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 Zorix-official/Zorix-Nano-0.8B-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 Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_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 Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_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 Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M

Use Docker

docker model run hf.co/Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M

LM Studio
Jan
Ollama
How to use Zorix-official/Zorix-Nano-0.8B-GGUF with Ollama:
```
ollama run hf.co/Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M
```

Unsloth Studio

How to use Zorix-official/Zorix-Nano-0.8B-GGUF 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 Zorix-official/Zorix-Nano-0.8B-GGUF 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 Zorix-official/Zorix-Nano-0.8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Zorix-official/Zorix-Nano-0.8B-GGUF to start chatting

How to use Zorix-official/Zorix-Nano-0.8B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_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": "Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Zorix-official/Zorix-Nano-0.8B-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 Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_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 Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Zorix-official/Zorix-Nano-0.8B-GGUF with Docker Model Runner:
```
docker model run hf.co/Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M
```

Lemonade

How to use Zorix-official/Zorix-Nano-0.8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Zorix-official/Zorix-Nano-0.8B-GGUF:Q5_K_M

Run and chat with the model

lemonade run user.Zorix-Nano-0.8B-GGUF-Q5_K_M

List all available models

lemonade list

Zorix Nano 0.8B

Zorix Nano 0.8B is a compact multilingual language model developed by Zorix.

Official website: https://zorix.it
Developer: Zorix
Architecture: zorix-nano
Parameters: approximately 0.8B
Format: GGUF
Quantization: Q5_K_M
Languages: Chinese, English and Italian

Runtime requirement

This model is officially supported only by:

Zorix GGUF Run

The model uses the custom architecture identifier:

general.architecture = zorix-nano

It is not designed for standard third-party GGUF runtimes.

Unsupported applications include:

- llama.cpp
- Ollama
- LM Studio
- GPT4All
- Transformers
- Other standard GGUF applications

Third-party runtimes may report:

unknown model architecture: zorix-nano

Use this model

Supported platforms

Platform| Architecture| Status
Linux| ARM64 / AArch64| Supported
Debian| ARM64 / AArch64| Supported
Ubuntu| ARM64 / AArch64| Supported
Android Termux| ARM64| Supported with Android runtime
Linux x86_64 / AMD64| Not currently supported| 
Windows| Not currently supported| 
macOS| Not currently supported| 

Linux ARM64 installation

This installation method supports ARM64 Linux distributions using glibc, including Debian and Ubuntu.

Install required tools:

sudo apt update
sudo apt install -y curl ca-certificates libgomp1

Create the Zorix directories:

mkdir -p "$HOME/.zorix/bin"
mkdir -p "$HOME/.zorix/models"

Download the Linux ARM64 runtime:

curl -L \
  "https://huggingface.co/Zorix-official/Zorix-Nano-0.8B-GGUF/resolve/main/runtime/linux-arm64/zorix-runtime-linux-arm64" \
  -o "$HOME/.zorix/bin/zorix-runtime"

Download the Zorix GGUF Run launcher:

curl -L \
  "https://huggingface.co/Zorix-official/Zorix-Nano-0.8B-GGUF/resolve/main/runtime/linux-arm64/zorix-gguf-run" \
  -o "$HOME/.zorix/bin/zorix-gguf-run"

Make both files executable:

chmod +x \
  "$HOME/.zorix/bin/zorix-runtime" \
  "$HOME/.zorix/bin/zorix-gguf-run"

Download Zorix Nano:

curl -L \
  "https://huggingface.co/Zorix-official/Zorix-Nano-0.8B-GGUF/resolve/main/zorix-nano-0.8b-q5_k_m.gguf" \
  -o "$HOME/.zorix/models/zorix-nano-0.8b-q5_k_m.gguf"

Add Zorix GGUF Run to the current shell:

export PATH="$HOME/.zorix/bin:$PATH"

To make the command available permanently:

echo 'export PATH="$HOME/.zorix/bin:$PATH"' >> "$HOME/.bashrc"
source "$HOME/.bashrc"

Check the installation:

zorix-gguf-run --version

Start interactive mode:

zorix-gguf-run

Run a single prompt:

zorix-gguf-run -p "你好，请介绍一下你自己。"

Italian example:

zorix-gguf-run -p "Ciao, presentati brevemente."

English example:

zorix-gguf-run -p "Introduce yourself briefly."

Custom options

-m, --model PATH       Select a Zorix GGUF model
-p, --prompt TEXT      Send a prompt
-t, --threads N        Set CPU thread count
-c, --context N        Set context size
-n, --tokens N         Set maximum output tokens
    --temp NUMBER      Set generation temperature
    --no-chat          Disable conversation mode
-v, --version          Show version
-h, --help             Show help

Example:

zorix-gguf-run \
  -p "Explain artificial intelligence simply." \
  -t 4 \
  -c 2048 \
  -n 256 \
  --temp 0.7

Android and Termux

The Linux runtime cannot run directly in native Android Termux because Linux uses glibc while Android uses Bionic.

Android users must use the separate Android ARM64 edition of Zorix GGUF Run located under:

runtime/android-arm64/

Do not install the Linux ARM64 executable directly in native Termux.

Runtime files

File| Description
"runtime/linux-arm64/zorix-runtime-linux-arm64"| Linux ARM64 inference runtime
"runtime/linux-arm64/zorix-gguf-run"| Linux ARM64 launcher
"zorix-nano-0.8b-q5_k_m.gguf"| Zorix Nano Q5_K_M model
"config.json"| Model information
"LICENSE"| Repository license

Runtime dependencies

The Linux ARM64 runtime dynamically uses:

- GNU C Library ("libc6")
- GNU C++ Standard Library ("libstdc++6")
- GNU OpenMP Runtime ("libgomp1")
- GCC Runtime Library ("libgcc-s1")

For Debian and Ubuntu:

sudo apt install -y libc6 libstdc++6 libgomp1 libgcc-s1

Intended use

Zorix Nano may be used for:

- Local conversational assistance
- Offline text generation
- Lightweight multilingual tasks
- Educational demonstrations
- Research and development
- ARM64 Linux experiments

Limitations

Zorix Nano may:

- Generate inaccurate information
- Misunderstand complex instructions
- Produce repetitive output
- Perform worse than larger models
- Generate biased or unsuitable content

Important output should be reviewed before use.

The model is not a replacement for qualified medical, legal, financial or safety professionals.

License

This repository is distributed under the included license.

Zorix GGUF Run contains applicable third-party open-source components and notices.

Developer

Zorix

Official website:

https://zorix.it

Model repository:

https://huggingface.co/Zorix-official/Zorix-Nano-0.8B-GGUF

Downloads last month: 619

GGUF

Model size

0.8B params

Architecture

zorix-nano

Hardware compatibility

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support