Zen Agent 4b

Compact 4B agent model with strong function calling and tool-use capabilities.

Overview

Fine-tuned from Qwen3-4B-Instruct-2507 (Apache 2.0) with Hanzo identity + agentic-data training + abliteration. Dense Qwen3 architecture, 4B parameters, 256K-token context.

Developed by Hanzo AI and the Zoo Labs Foundation.

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zenlm/zen-agent-4b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [{"role": "user", "content": "Hello!"}]
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][inputs.input_ids.shape[1]:], skip_special_tokens=True))

API Access

curl https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "zen-agent-4b", "messages": [{"role": "user", "content": "Hello"}]}'

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

Model Details

Credits

Fine-tuned from Qwen/Qwen3-4B-Instruct-2507 by Qwen (Alibaba Cloud), licensed under Apache 2.0. Hanzo adds identity training, agentic-data fine-tuning, and abliteration.

License

Apache 2.0 — inherited from the Qwen3-4B-Instruct-2507 base model.