@Alibaba_Qwen
๐ Introducing the Qwen 3.5 Medium Model Series Qwen3.5-Flash ยท Qwen3.5-35B-A3B ยท Qwen3.5-122B-A10B ยท Qwen3.5-27B โจ More intelligence, less compute. โข Qwen3.5-35B-A3B now surpasses Qwen3-235B-A22B-2507 and Qwen3-VL-235B-A22B โ a reminder that better architecture, data quality, and RL can move intelligence forward, not just bigger parameter counts. โข Qwen3.5-122B-A10B and 27B continue narrowing the gap between medium-sized and frontier models โ especially in more complex agent scenarios. โข Qwen3.5-Flash is the hosted production version aligned with 35B-A3B, featuring: โ 1M context length by default โ Official built-in tools ๐ Hugging Face: https://t.co/wFMdX5pDjU ๐ ModelScope: https://t.co/9NGXcIdCWI ๐ Qwen3.5-Flash API: https://t.co/82ESSpaqAF Try in Qwen Chat ๐ Flash: https://t.co/UkTL3JZxIK 27B: https://t.co/haKxG4lETy 35B-A3B: https://t.co/Oc1lYSTbwh 122B-A10B: https://t.co/hBMODXmh1o Would love to hear what you build with it.