Mistral Small 3.2 24B Instruct 2506
Mistral develops the Mistral Small 3.2 24B Instruct 2506, a chat model exceling at following precise instructions and reducing repetition errors, with a notable context window of 131,072 tokens. It demonstrates improved performance in instruction following, achieving a Wildbench v2 score of 65.33% and an IF accuracy score of 84.78%.
Input
Output
Context
131K
Max Output
16K
Parameters
24B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Benchmarks
Estimated GPU Requirements for Mistral Small 3.2 24B Instruct 2506
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Mistral
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 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.