metadata
license: apache-2.0
language:
- en
- zh
- ja
- ko
- fr
- de
- es
- pt
- ru
- ar
tags:
- zen4
- zenlm
- hanzo
- frontier-ai
- abliterated
base_model: huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated
pipeline_tag: text-generation
library_name: transformers
Zen4 Max
Zen4 Max is a 35B MoE (3B active) parameter language model from the Zen4 family by Zen LM and Hanzo AI.
Built on abliterated (uncensored) weights with Zen4 Frontier architecture for unrestricted, open-ended AI assistance.
Model Details
| Property | Value |
|---|---|
| Parameters | 35B MoE total, 3B active |
| Architecture | Zen4 Frontier |
| Context | 262K tokens |
| License | APACHE-2.0 |
| Family | Zen4 |
| Tier | Medium |
| Creator | Zen LM / Hanzo AI |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("zenlm/zen4-max", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen4-max")
messages = [{"role": "user", "content": "Hello, who are you?"}]
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))
Zen4 Family
| Model | Parameters | Context | HuggingFace |
|---|---|---|---|
| Zen4 Nano | 0.8B | 262K | zenlm/zen4-nano |
| Zen4 Micro | 2B | 262K | zenlm/zen4-micro |
| Zen4 Mini | 4B | 262K | zenlm/zen4-mini |
| Zen4 | 9B | 262K | zenlm/zen4 |
| Zen4 Pro | 27B | 262K | zenlm/zen4-pro |
| Zen4 Max | 35B MoE (3B active) | 262K | zenlm/zen4-max |
| Zen4 Coder Flash | 31B MoE (3B active) | 131K | zenlm/zen4-coder-flash |
| Zen4 Pro Max | 80B MoE (3B active) | 256K | zenlm/zen4-pro-max |
| Zen4 Coder | 80B MoE (3B active) | 256K | zenlm/zen4-coder |
| Zen4 Mega | 122B MoE (10B active) | 262K | zenlm/zen4-mega |
| Zen4 Thunder | 230B MoE (10B active) | 1M | zenlm/zen4-thunder |
| Zen4 Storm | 456B MoE (45B active) | 1M | zenlm/zen4-storm |
| Zen4 Titan | 744B MoE (40B active) | 128K | zenlm/zen4-titan |
| Zen4 Ultra | 1.04T MoE (32B active) | 256K | zenlm/zen4-ultra |
| Zen4 Ultra Max | 1T MoE (50B active) | 128K | zenlm/zen4-ultra-max |
Links
Zen AI: Clarity Through Intelligence