The Qwen team has open-sourced the Qwen 3.8-2.4T-A95B model weights.

The Qwen team has open-sourced the Qwen3.8-2.4T-A95B model, marking the first time weights have been made available at the Qwen-Max level. This MoE model has a total of 2.4T parameters, 95B activations per token, and natively supports 256K context, significantly enhancing capabilities for programming, office work, research, and long-cycle agents. It has achieved leading performance in multiple benchmarks, including PaperBench and TerminalBench, and supports deployment with frameworks such as SGLang and vLLM. It features a default thinking mode and supports adjustable inference depth.