Magistral Small 2506
Mistral's Magistral Small 2506 is a chat model that excels at handling long chains of reasoning, supporting dozens of languages, and is licensed under Apache 2.0, allowing for flexible usage and modification. With 24B parameters, it features a notable context window of up to 40,960 tokens, although performance may degrade past this point.
Input
Output
Context
41K
Max Output
40K
Parameters
23.6B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Estimated GPU Requirements for Magistral Small 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.