qwen3-coder-480b-a35b-instruct
Qwen develops the Qwen3 Coder 480B A35B Instruct, a chat model capable of streaming, web search, code execution, function calling, and structured output. It is genuinely best at handling complex tasks with its large context window of 262,144 tokens.
Input
Output
Context
1049K
Max Output
262K
Parameters
480B
Technical Specifications
Model TypeCode
Context Window1,048,576 tokens
Max Output Tokens262,144 tokens
Parameters480B
Release DateJul 22, 2025
Training CutoffJun 1, 2025
LicenseApache 2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
4.4%
HLE
47.7%
AIME
61.8%
GPQA
35.9%
SciCode
94.2%
MATH 500
78.8%
MMLU Pro
39.3
Math
24.6
Coding
58.5%
LiveCodeBench
18.0
Intelligence
66.6
Speed (tok/s)
1.5
TTFA (s)
1.5
TTFT (s)
Resources & Links
Estimated GPU Requirements for qwen3-coder-480b-a35b-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.