Skip to content
Hacker News · AI·· 1 h agoAI score62

Tencent Hy4 Flash: 295B-parameter MoE model with 256K context and configurable reasoning

Tencent Hy4 Flash

AI summary

Tencent's Hy4 Flash is a 295B-parameter Mixture-of-Experts model with 21B active parameters, 192 experts and top-8 routing, built for reasoning, agentic workflows and production use. It offers a default no-think mode plus low and high chain-of-thought modes, a 256K context window, and stable tool-calling that generalizes across agent scaffoldings, with Tencent emphasizing grounded, anti-hallucination behavior.

Source:Hacker News · AI · openrouter.ai