Blog

• LLM Architecture Explained: The Blocks Open Models Share
  Why do Llama, DeepSeek, gpt-oss and Qwen look so alike? The four blocks nearly every open LLM shares, why the recipe stuck, and where models break from it.
• Qwen3.8-27B vs Claude Opus 4.6: How a 27B Model Competes
  How does a 27B open model beat Claude Opus 4.6 Max at agentic coding and computer use? Inside Qwen3.8-27B, and what training added.