Qwen 3 Coder 30B A3B Instruct
Qwen develops the Qwen 3 Coder 30B A 3B Instruct, a chat model exceling in coding tasks such as code completion, generation, and review, with notable performance on Agentic Coding and Agentic Browser-Use. Its long-context capabilities, supporting up to 262,144 tokens natively, enable repository-scale understanding.
Input
Output
Context
262K
Max Output
33K
Parameters
30.5B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens32,768 tokens
Parameters30.5B
Release DateJul 31, 2025
Training CutoffJun 1, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.0%
HLE
29.7%
AIME
51.6%
GPQA
27.8%
SciCode
89.3%
MATH 500
70.6%
MMLU Pro
29.0
Math
19.4
Coding
40.3%
LiveCodeBench
13.6
Intelligence
109
Speed (tok/s)
1.6
TTFA (s)
1.6
TTFT (s)
Resources & Links
Estimated GPU Requirements for Qwen 3 Coder 30B A3B Instruct
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.