---
library_name: transformers
pipeline_tag: text-generation
base_model: Qwen/Qwen3-8B
tags:
  - text-generation
  - conversational
  - multilingual
  - zen
  - zen3
  - hanzo
  - zenlm
license: apache-2.0
language:
- en
---

# zen3-nano

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

Repackaged from [Qwen/Qwen3-8B](https://huggingface.co/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

```python
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:

```python
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)
```

Get your API key at [console.hanzo.ai](https://console.hanzo.ai) — $5 free credit on signup.

## License

`apache-2.0`. Upstream: **Qwen/Qwen3-8B** by Alibaba Qwen. Upstream LICENSE/NOTICE retained in-repo.

---

*Zen LM is developed by [Hanzo AI](https://hanzo.ai) — Frontier AI infrastructure.*