zenlm/zen-eco-4b-instruct

zen-eco-instruct

Efficient instruction-following

Model Details

• Size: 4B
• Base: Qwen/Qwen3-4B
• Org: Hanzo AI × Zoo Labs Foundation
• License: Apache 2.0
• Code: https://github.com/zenlm/zen-eco-instruct

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

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

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

Links

• GitHub Org
• Training: Zen Gym
• Inference: Zen Engine
• Model Repo

---

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