Qwen/Qwen3-30B-A3B-Instruct-2507

Qwen/Qwen3-30B-A3B-Instruct-2507 is a 30.5 billion parameter (3.3B activated) causal language model from the Qwen3 family, developed by Qwen. This instruction-tuned model features a native 262,144 token context length, with experimental support for up to 1 million tokens using Dual Chunk Attention and MInference. It demonstrates significant improvements in instruction following, logical reasoning, mathematics, coding, and long-tail knowledge across multiple languages, making it suitable for complex analytical and generative tasks.