Qwen3 Coder 30B A3B Instruct
Qwen's 30B MoE code-focused LLM for code generation and completion with a 160k-token context.
Model Card
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
Author
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Author
Get the full context.
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.