Alibaba Group@AlibabaGroupIntroducing Qwen3.8-Max, the largest and most capable flagship model to date! With 2.4 trillion parameters and a 1 million-token context window, it is designed for advanced coding, real-world tasks, in-depth research, and tackling long-horizon challenges. #AlibabaAI #QwenOpens with an announcement
Alibaba Group@AlibabaGroup🚀 Qwen3.6‑27B is now open source! Start building with this dense 27B multimodal model delivering flagship‑level agentic coding performance. #AlibabaAI #QwenOpens with an observation
Alibaba Group@AlibabaGroupAlibaba opens the weights for Qwen3.8-Flash, a multimodal MoE model previewing Qwen4’s architecture. With systematic upgrades in attention, residuals, embedding, and optimization, it enhances performance, efficiency, and stability. #AlibabaAI #QwenOpens with an observation