Qwen3 Coder 30B A3B Instruct

Qwen · qwen/qwen3-coder-30b-a3b-instruct

← Back to leaderboard

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...

open weightstexttext->text

Context

Max context: 160000
Max output: 32768

Pricing

Input / 1M: 0.07
Output / 1M: 0.27
Blend / 1M: 0.17

Quality

Quality index:

Provider

Provider: Qwen
Moderated: no