Discover Mistral Small 3.2 24B Model

Versatile model for text and image processing with structured outputs.

Input: image · text Output: text Context: 131,072 tokens Release: 2025-06-20

Mistral Small 3.2 24B by Mistral, released on June 20, 2025, is a powerful model designed for text and image inputs with a focus on instruction following and structured outputs. It boasts a large context window of 131072 tokens, allowing it to handle extensive data inputs efficiently. This model excels in reducing repetition and infinite generations, making it particularly reliable for complex tasks. With support for coding, STEM, and vision benchmarks, it offers robust performance across various domains. Key features include function and tool calling capabilities, enhancing its utility in diverse applications.

Use Cases

Here are a few ways teams apply Mistral: Mistral Small 3.2 24B (free) in practice—from fast drafting to multimodal understanding. Adapt these ideas to your workflow.

Generate structured outputs from complex inputs

Improve coding tasks with HumanEval+ support

Enhance STEM learning with accurate responses

Process images for detailed analysis

Utilize tool calling for advanced applications

Key Features

A quick look at the capabilities that make this model useful in real projects.

Optimized for instruction following

Large 131072 token context window

Supports text and image inputs

Enhanced function and tool calling

Improved accuracy on WildBench and Arena Hard

Specs

Overview

Vendor
mistralai

Model ID
mistralai/mistral-small-3.2-24b-instruct:free

Release
2025-06-20

Modalities & context

Input
image · text

Output
text

Context
131,072 tokens

Parameters & defaults

Supported parameters: frequency_penalty, max_tokens, presence_penalty, repetition_penalty, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p

Defaults: temperature 0.3, top_p 0.95

Benchmark tests: Mistral: Mistral Small 3.2 24B (free)

We ran this model against a few representative prompts to show its range. Review the outputs below and be the judge.

Text

Prompt:

Write 150 words on how AI might positively upend work, leisure and creativity

The Mistral Small 3.2 24B is a compact language model designed for a variety of natural language processing tasks. With 24 billion parameters, it offers a balance between performance and resource efficiency, making it suitable for applications such as text generation, summarization, and conversational agents. This model is particularly useful for developers and researchers looking to integrate advanced language capabilities into their projects without requiring extensive computational resources. Notably, while the Mistral Small 3.2 24B can handle a wide range of topics and contexts, its performance may vary based on the complexity of the input and the specificity of the task. Users should be aware that, like many language models, it may generate outputs that require human oversight for accuracy and appropriateness. Additionally, the model is available for free, making it accessible for experimentation and development purposes.

Run this prompt on Upend.AI

Image

Prompt:

Generate an SVG of a pelican riding a bicycle.

Run this prompt on Upend.AI

Ready to try Mistral: Mistral Small 3.2 24B (free)?

Chat with Mistral: Mistral Small 3.2 24B

up.end

/ˌəpˈend/

verb

To “upend” means to completely disrupt, overturn, or drastically change the established order or structure of something. It implies a significant shift or alteration that can potentially have far-reaching consequences. When something is upended, it is turned upside down or transformed in a way that challenges conventional norms or expectations. The term often carries a sense of innovation, transformation, and sometimes even a hint of upheaval, indicating that the changes are not just minor adjustments but rather a fundamental reimagining of the status quo.

Privacy Terms