qwen3-235b-a22b-thinking-2507
Qwen's Qwen3 235B A22B Thinking 2507 FP8 is a chat model capable of streaming, function calling, extended thinking, and producing structured output, with a context window of 262,144 tokens. It excels in mathematical tasks, as evidenced by its top 25% or better scores in Math Index, MMLU-Pro, LiveCodeBench, AIME, and MATH-500. Notably, its architecture supports an exceptionally large context window, allowing it to process and respond to lengthy inputs.
Input
Output
Context
262K
Max Output
262K
Parameters
235B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Benchmarks
Resources & Links
Estimated GPU Requirements for qwen3-235b-a22b-thinking-2507
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Qwen
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jul 30, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.