Instructions to use zenlm/zen-nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zenlm/zen-nano with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zenlm/zen-nano")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-nano")
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-nano")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use zenlm/zen-nano with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="zenlm/zen-nano",
	filename="gguf/zen-nano-0.6b-Q4_K_M.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use zenlm/zen-nano with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf zenlm/zen-nano:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf zenlm/zen-nano:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/zenlm/zen-nano:Q4_K_M

LM Studio
Jan

vLLM

How to use zenlm/zen-nano with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/zenlm/zen-nano:Q4_K_M

SGLang

How to use zenlm/zen-nano with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "zenlm/zen-nano" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zenlm/zen-nano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "zenlm/zen-nano" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zenlm/zen-nano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use zenlm/zen-nano with Ollama:
```
ollama run hf.co/zenlm/zen-nano:Q4_K_M
```

Unsloth Studio new

How to use zenlm/zen-nano 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 zenlm/zen-nano 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 zenlm/zen-nano to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for zenlm/zen-nano to start chatting

Pi new

How to use zenlm/zen-nano with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf zenlm/zen-nano: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": "zenlm/zen-nano:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zenlm/zen-nano with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf zenlm/zen-nano: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 zenlm/zen-nano:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use zenlm/zen-nano with Docker Model Runner:
```
docker model run hf.co/zenlm/zen-nano:Q4_K_M
```

Lemonade

How to use zenlm/zen-nano with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull zenlm/zen-nano:Q4_K_M

Run and chat with the model

lemonade run user.zen-nano-Q4_K_M

List all available models

lemonade list

Zen Nano 0.6B

Zen Nano is an ultra-lightweight 0.6B parameter language model optimized for edge devices and mobile deployment. A compact foundation model that delivers impressive performance in a tiny package.

Model Details

Model Type: Causal Language Model
Architecture: 0.6B dense transformer
Parameters: 0.6 billion
License: Apache 2.0
Languages: English, Chinese
Context Length: 32K tokens
Developed by: Zen AI Team (Hanzo AI)

Capabilities

💡 Lightweight: Only 0.6B parameters for edge deployment
📱 Mobile-Ready: Runs on smartphones and IoT devices
⚡ Fast: 44K tokens/sec on M3 Max (MLX)
🔋 Efficient: Low power consumption
🌐 Multilingual: English and Chinese support
📦 Multiple Formats: PyTorch, MLX, GGUF (Q2_K to F16)
🎯 32K Context: Extended context window

Performance

Throughput

M3 Max (MLX): 44,000 tokens/sec
RTX 4090 (GGUF Q4): 35,000 tokens/sec
iPhone 15 Pro: 8,000 tokens/sec
Raspberry Pi 5: 2,500 tokens/sec

Memory Usage

Format	VRAM/RAM
Q2_K	0.3GB
Q4_K_M	0.4GB
Q8_0	0.7GB
F16	1.2GB

Use Cases

Edge AI applications
Mobile chatbots
IoT device intelligence
Offline AI assistants
Resource-constrained environments
Real-time inference
Embedded systems

Installation

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "zenlm/zen-nano-0.6b",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-nano-0.6b")

MLX (Apple Silicon)

from mlx_lm import load, generate

model, tokenizer = load("zenlm/zen-nano-0.6b")
response = generate(model, tokenizer, prompt="Hello!", max_tokens=100)

GGUF (llama.cpp)

./llama-cli -m zen-nano-0.6b-Q4_K_M.gguf -p "Hello!" -n 100

Zen Engine

zen-engine serve --model zenlm/zen-nano-0.6b --port 3690

Training with Zen Gym

Fine-tune Zen Nano for your use case:

cd /path/to/zen-gym

llamafactory-cli train \
    --config configs/zen_nano_lora.yaml \
    --dataset your_dataset

Benchmarks

Task	Score	Notes
MMLU	35.2%	5-shot
GSM8K	28.4%	8-shot CoT
HumanEval	24.1%	pass@1
MATH	18.7%	4-shot

Limitations

Smaller capacity than larger models
May struggle with complex reasoning
Limited specialized knowledge
Best for short-to-medium contexts
Quantization reduces quality slightly

Citation

@misc{zennano2025,
  title={Zen Nano: Ultra-Lightweight Language Model},
  author={Zen AI Team},
  year={2025},
  howpublished={\url{https://huggingface.co/zenlm/zen-nano-0.6b}}
}

Part of the Zen AI ecosystem.

Citation

@misc{zenlm2025zen-nano,
    title={Zen LM: zen-nano},
    author={Hanzo AI and Zoo Labs Foundation},
    year={2025},
    publisher={HuggingFace},
    howpublished={\url{https://huggingface.co/zenlm/zen-nano}}
}

Abliteration

Zen Nano 0.6B weights are derived from an abliterated base model. Abliteration removes refusal behavior by identifying and nullifying the "refusal direction" in the model's residual stream, as described in Maxime Labonne's methodology.

Method: Directional ablation on the residual stream across all layers Source: Zen MoDE (Mixture of Distilled Experts) architecture base Effect: Removes refusal behaviors while preserving all other capabilities Identity layer: Zen identity added via system prompt — full LoRA fine-tuning planned

Abliteration is a feature, not a limitation. It enables unrestricted research, security testing, and applications where safety guardrails are managed at the application layer rather than baked into model weights.

Downloads last month: 70

Safetensors

Model size

0.6B params

Tensor type

BF16

zenlm
/

zen-nano

Zen Nano 0.6B

Model Details

Capabilities

Performance

Throughput

Memory Usage

Use Cases

Installation

Transformers

MLX (Apple Silicon)

GGUF (llama.cpp)

Zen Engine

Training with Zen Gym

Benchmarks

Limitations

Citation

Links

Part of the Zen AI ecosystem.

Citation

Abliteration