🧰 Qwen3.6-27B

The items that name it 5

• [AINews] DeepSeek DeepInfer: Open Source SOTA Inference running 155T toks/day/cluster making $22m/day at ~80% margin for a 81 day payback
  article2026-10-21
• [AINews] DeepSeek DeepInfer: Open Source SOTA Inference running 155T toks/day/cluster making $22m/day at ~80% margin for a 81 day payback
  article2026-10-21
• Transformers now runs llama.cpp quants
  article2026-09-22It is written here as Qwen3.6 27B.
• Mapika/decider
  repo2026-09-16
• GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis
  paper

In every workspace you can read 6