Instructions to use zenlm/zen3-nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zenlm/zen3-nano with Transformers:

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

pipe = pipeline("text-generation", model="zenlm/zen3-nano")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zenlm/zen3-nano")
model = AutoModelForCausalLM.from_pretrained("zenlm/zen3-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zenlm/zen3-nano with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zenlm/zen3-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/zen3-nano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zenlm/zen3-nano

SGLang

How to use zenlm/zen3-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/zen3-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/zen3-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/zen3-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/zen3-nano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zenlm/zen3-nano with Docker Model Runner:
```
docker model run hf.co/zenlm/zen3-nano
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

zen3-nano

Compact, capable language model for fast inference, part of the OSS-clean Zen model line.

Repackaged from Qwen/Qwen3-8B (apache-2.0, Alibaba Qwen). Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.

Specs

Property	Value
Parameters	8B (dense)
Architecture	Qwen3 (`Qwen3ForCausalLM`)
Context Length	40K tokens
Generation	Zen3

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("zenlm/zen3-nano", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen3-nano")

messages = [{"role": "user", "content": "Explain quantum computing in simple terms."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

API Access

Also served via the Hanzo AI API:

from openai import OpenAI

client = OpenAI(base_url="https://api.hanzo.ai/v1", api_key="YOUR_KEY")
response = client.chat.completions.create(
    model="zen3-nano",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)