---
language:
- en
license: apache-2.0
tags:
- zen-lm
- transformers
- safetensors
base_model: Qwen/Qwen3-0.6B
pipeline_tag: text-generation
---

# zen-nano

Ultra-lightweight edge AI

## Model Details

- **Size**: 0.6B
- **Base**: Qwen/Qwen3-0.6B
- **Org**: Hanzo AI × Zoo Labs Foundation
- **License**: Apache 2.0
- **Code**: https://github.com/zenlm/zen-nano

## Quick Start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("zenlm/zen-nano")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-nano")

inputs = tokenizer("Hello!", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))
```

## Links

- [GitHub Org](https://github.com/zenlm)
- [Training: Zen Gym](https://github.com/zenlm/gym)
- [Inference: Zen Engine](https://github.com/zenlm/engine)
- [Model Repo](https://github.com/zenlm/zen-nano)

---

**Zen LM** • Building AI that's local, private, and free