Qwen3.8-2.4T

Alibaba has released Qwen3.8, its most capable open-source model to date, featuring 2.4 trillion total parameters with 95 billion activated parameters and improved performance in coding, professional work, research, and agentic tasks. The model is available in FP8-quantized format compatible with popular inference frameworks like vLLM and SGLang, with a native context length of 262,144 tokens extensible to over 1 million tokens. Qwen3.8 introduces new capabilities including flexible reasoning control, better agent execution for multi-step task completion, and an official managed version called Qwen3.8-Max available through Qwen Cloud.