Zen4-Mini is a 4B-parameter dense language model optimized for edge deployment, mobile applications, and resource-constrained environments. It delivers strong reasoning and instruction-following in a compact footprint.

This model is part of the Zen4 model family:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "zenlm/zen4-mini"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Explain the difference between supervised and unsupervised learning."}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
inputs = tokenizer([text], return_tensors="pt").to(model.device)

output_ids = model.generate(**inputs, max_new_tokens=512)
generated = output_ids[0][len(inputs.input_ids[0]):]
print(tokenizer.decode(generated, skip_special_tokens=True))

Ideal for: laptops, edge devices, single-consumer GPU setups, and mobile inference runtimes.

Zen4-Mini weights are derived from an abliterated base model. Abliteration removes refusal behavior by identifying and nullifying the "refusal direction" in the model's residual stream.

Method: Directional ablation on the residual stream across all layers Implementation: hanzoai/remove-refusals — Hanzo's production abliteration toolkit Technique: Refusal in LLMs is mediated by a single direction — Arditi et al. Effect: Removes refusal behaviors while preserving all other capabilities Identity layer: Zen identity added via system prompt — full LoRA fine-tuning planned

Abliteration is a feature, not a limitation. It enables unrestricted research, security testing, and applications where safety guardrails are managed at the application layer rather than baked into model weights.

@misc{zen4mini2025,
  title        = {Zen4-Mini: 4B Dense Language Model for Edge Deployment},
  author       = {{Hanzo AI} and {Zoo Labs Foundation}},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/zenlm/zen4-mini}},
  note         = {Apache 2.0 License}
}

Part of the Zen model family by Hanzo AI (Techstars '17) and Zoo Labs Foundation.