Blog

GITHUB HUGGING FACE All Zen models are built on Zen MoDE: Mixture of Distilled Experts. This post explains the architecture, why we chose it, and how distillation and expert routing interact to deliver frontier capability at practical inference cost. The Core Problem There is a fundamental tension in large model design: More parameters → better capability More parameters → higher inference cost Dense scaling laws are well established. Doubling parameters roughly halves perplexity (with sufficient data), but doubles inference FLOP....

GITHUB HUGGING FACE TRY ZEN CHAT Today we are announcing Zen LM — a family of open frontier models co-developed by Hanzo AI and Zoo Labs Foundation. This release marks the public launch of the Zen model catalog: 94+ models spanning text, vision, audio, and code, all built on our Zen MoDE (Mixture of Distilled Experts) architecture. Why We Built It Modern AI infrastructure concentrates capability in a small number of proprietary systems....

Tech Report GitHub Hugging Face ModelScope DISCORD Introduction We are excited to introduce Qwen3Guard, the first safety guardrail model in the Qwen family. Built upon the powerful Qwen3 foundation models and fine-tuned specifically for safety classificatoin, Qwen3Guard ensures responsible AI interactions by delivering precise safety detection for both prompts and responses, complete with risk levels and categorized classifications for accurate moderation. Qwen3Guard achieves state-of-the-art performance on major safety benchmarks, demonstrating strong capabilities in both prompt and response classification tasks across English, Chinese, and multilingual environments....

QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD We are excited to introduce Qwen-Image-Edit, the image editing version of Qwen-Image. Built upon our 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image’s unique text rendering capabilities to image editing tasks, enabling precise text editing. Furthermore, Qwen-Image-Edit simultaneously feeds the input image into zen-VL (for visual semantic control) and the VAE Encoder (for visual appearance control), achieving capabilities in both semantic and appearance editing....

GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD We are thrilled to release Qwen-Image, a 20B MMDiT image foundation model that achieves significant advances in complex text rendering and precise image editing. To try the latest model, feel free to visit Qwen Chat and choose “Image Generation”. The key features include: Superior Text Rendering: Qwen-Image excels at complex text rendering, including multi-line layouts, paragraph-level semantics, and fine-grained details. It supports both alphabetic languages (e....