Models

GITHUB HUGGING FACE TRY ZEN CHAT Zen4 Ultra is the most capable model in the Zen4 family. It is a Mixture of Distilled Experts model with 480B total parameters and 35B active parameters per forward pass. The native context window is 256K tokens, extending to 1M tokens with YaRN extrapolation. Architecture Property Value Total parameters 480B Active parameters per token 35B Experts per layer 128 Top-k routing 8 Context window (native) 256K Context window (YaRN) 1M Vocabulary size 151,936 Attention heads 64 KV heads (GQA) 8 Layers 94 Benchmark Results General Reasoning Benchmark Zen4 Ultra Zen Max 72B MMLU 89....

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....

Today we release Zen 3.0, our third-generation language model family. Zen 3 represents a step change in what open models can do. Model Family Zen 3 comes in several sizes: Model Parameters Context Training Tokens Zen-3-8B 8.1B 128K 15T Zen-3-32B 32.5B 128K 12T Zen-3-72B 72.3B 128K 10T Zen-3-MoE 141B (24B active) 128K 14T All models use the same architecture with scaled dimensions. All are released under Apache 2.0. Architecture Highlights Extended Context All Zen 3 models support 128K token context natively:...