0
MODEL SIGNAL · QWEN

Qwen3-Coder-30B-A3B-Instruct

Qwen3-Coder-30B-A3B-Instruct is an open-weights Mixture-of-Experts (MoE) model optimized for software development tasks, designed for high inference efficiency and long-context processing.

CATEGORYCode
RELEASEDJuly 31, 2025
Key Features
  • Mixture-of-Experts (MoE) architecture with 30.5B total and 3.3B active parameters.
  • 262,144-token native context window.
  • Instruction-tuned specifically for coding, debugging, and general software engineering.
  • Openly accessible under the Apache 2.0 license.

Provider announcement →

Read the Model Signal report →

The designed Model Signal report for Qwen3-Coder-30B-A3B-Instruct is still in review. It will publish here after the fact and quality gates clear.