Skip to main content
Language model

Qwen3-Coder 480B-A35B Instruct

Alibaba

Released
April 2025
Data date
September 26, 2026

Qwen3-Coder 480B-A35B Instruct is the large open flagship checkpoint. Qwen highlights coding, browser use, and tool use, with a purpose-built function-calling format for coding agents. Its Mixture-of-Experts architecture contains 480 billion parameters and activates 35 billion per token.

Native context reaches 262,144 tokens and can be extended to 1 million with YaRN. Qwen optimizes the checkpoint for repository-scale understanding. Qwen3-Coder 30B-A3B Instruct is the smaller sibling.

Specifications and access

SpecificationValue and source
Weights
Open weightsSource
Access
APISource
Parameters
480 billionSource
Active parameters
35 billionSource
Context window
262,144 tokensSource
Maximum output
65,536 tokensSource
Knowledge Cutoff
April 2025Source
License
Apache 2.0Source
Inputs
TextSource
Outputs
TextSource
Tool calling
YesSource