qwen3-235b-a22b-2507
Qwen's Qwen3 235B A22B Instruct 2507 is a chat model capable of streaming, web search, code execution, function calling, and structured output. It is genuinely best at handling complex mathematical problems, as evidenced by its top 25% score on the MATH-500 benchmark.
Input
Output
Context
262K
Max Output
16K
Parameters
235B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens16,384 tokens
Parameters235B
Release DateJul 21, 2025
Training CutoffJun 1, 2025
LicenseApache 2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
15.0%
HLE
94.0%
AIME
79.0%
GPQA
42.4%
SciCode
98.4%
MATH 500
84.3%
MMLU Pro
91.0
Math
23.2
Coding
78.8%
LiveCodeBench
22.3
Intelligence
53.7
Speed (tok/s)
38.6
TTFA (s)
1.4
TTFT (s)
Resources & Links
Estimated GPU Requirements for qwen3-235b-a22b-2507
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.