Qwen/Qwen3-Coder-Next

Qwen3-Coder-Next is an 80 billion parameter (3 billion activated) open-weight causal language model developed by Qwen, specifically engineered for coding agents and local development. It features a massive 262,144 token context length and a Mixture of Experts (MoE) architecture, enabling efficient performance comparable to much larger models. This model excels at long-horizon reasoning, complex tool usage, and recovery from execution failures, making it highly effective for dynamic coding tasks and seamless integration with various CLI/IDE platforms.