GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
zenlm
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
zenlm
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
Fine-tuned from Qwen/Qwen3-8B (Apache-2.0) with Hanzo identity training, agentic-data fine-tuning, and abliteration.
Developed by Hanzo AI and the Zoo Labs Foundation.
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "zenlm/zen-pro"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))
bash
curl https://api.hanzo.ai/v1/chat/completions \-H "Authorization: Bearer $HANZO_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "zen-pro", "messages": [{"role": "user", "content": "Hello"}]}'
Get your API key at console.hanzo.ai — $5 free credit on signup.
| Attribute | Value |
|---|---|
| Base model | Qwen/Qwen3-8B |
| Parameters | 8B |
| Architecture | Qwen3 (dense decoder-only transformer) |
| Context | 32,768 tokens (up to 131,072 with YaRN) |
| License | Apache 2.0 |
Built on Qwen3-8B by the Alibaba Qwen team, released under the Apache 2.0 license. Hanzo AI adds identity training, agentic-data fine-tuning, and abliteration on top of the upstream weights.
Apache 2.0 — inherited from the upstream Qwen3-8B base model.