Qwen/Qwen3.5-397B-A17B

Qwen3.5-397B-A17B is a causal language model with a vision encoder developed by Qwen, featuring 397 billion total parameters with 17 billion activated. It utilizes an efficient hybrid architecture combining Gated Delta Networks and sparse Mixture-of-Experts for high-throughput inference. This model excels in unified vision-language understanding, agentic capabilities, and supports an extended context length of 262,144 tokens, extensible up to 1,010,000 tokens, making it suitable for complex multimodal tasks and ultra-long text processing across 201 languages.