Instructions to use zenlm/zen4-thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zenlm/zen4-thinking with Transformers:

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

pipe = pipeline("text-generation", model="zenlm/zen4-thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zenlm/zen4-thinking")
model = AutoModelForCausalLM.from_pretrained("zenlm/zen4-thinking")
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

vLLM

How to use zenlm/zen4-thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zenlm/zen4-thinking"
# 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/zen4-thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zenlm/zen4-thinking

SGLang

How to use zenlm/zen4-thinking 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/zen4-thinking" \
    --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/zen4-thinking",
		"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/zen4-thinking" \
        --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/zen4-thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zenlm/zen4-thinking with Docker Model Runner:
```
docker model run hf.co/zenlm/zen4-thinking
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Zen4 Thinking

Zen LM by Hanzo AI — Chain-of-thought reasoning model with explicit thinking traces. Excels at math, logic, and step-by-step analysis.

Specs

Property	Value
Parameters	562B MoE
Context Length	262K tokens
Architecture	Zen MoDE (Mixture of Distilled Experts)
Generation	Zen4

API Access

This model is served exclusively via the Hanzo AI API. Weight downloads are not available for this model tier.

from openai import OpenAI

client = OpenAI(base_url="https://api.hanzo.ai/v1", api_key="YOUR_KEY")
response = client.chat.completions.create(
    model="zen4-thinking",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Get your API key at console.hanzo.ai — $5 free credit on signup.

License

Apache 2.0

Zen LM is developed by Hanzo AI — Frontier AI infrastructure.

Downloads last month: 24

Safetensors

Model size

81B params

Tensor type

BF16

Model tree for zenlm/zen4-thinking

Quantizations

2 models