Instructions to use zenlm/zen-3-nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen-3-nano with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zenlm/zen-3-nano")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zenlm/zen-3-nano", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use zenlm/zen-3-nano with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zenlm/zen-3-nano" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen-3-nano", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zenlm/zen-3-nano
- SGLang
How to use zenlm/zen-3-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-3-nano" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen-3-nano", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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-3-nano" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen-3-nano", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zenlm/zen-3-nano with Docker Model Runner:
docker model run hf.co/zenlm/zen-3-nano
Zen 3 Nano
Parameters: 0.6B | Architecture: Zen 3 Architecture | Context: 32K | License: Apache 2.0 | Released: 2024-09-01
Zen 3 generation label. Weights at zenlm/zen3-nano.
The Zen 3 family (Q3–Q4 2024) introduced sparse MoE routing and expanded to vision, audio, and multimodal reasoning.
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("zenlm/zen3-nano", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen3-nano")
ollama run hf.co/zenlm/zen3-nano
The Zen LM Family
Joint research collaboration:
- Hanzo AI (Techstars '17) — AI infrastructure, API gateway, inference optimization
- Zoo Labs Foundation (501c3) — Open AI research, ZIPs governance, decentralized training
- Lux Partners Limited — Compute coordination and settlement layer
All weights Apache 2.0. Download, run locally, fine-tune, deploy commercially.
HuggingFace · Chat free · API · Docs
Model tree for zenlm/zen-3-nano
Base model
zenlm/zen3-nano