Qwen3 Coder 30B A3B Instruct

Provider:Qwen

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...

Key specs

Token pricing

Modalities

Text

Use Cases

When to pick this model

Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.

FAQ

More models from Qwen

Full info:Qwen3 Coder 30B A3B Instruct