Explore the Mistral Small 3 AI Model

Fast and efficient text processing with Mistral Small 3.

Input: text Output: text Context: 32,768 tokens Release: 2025-01-30

Discover the Mistral Small 3, a 24B-parameter language model by Mistral AI, released on January 30, 2025. This model is designed for low-latency performance across various AI tasks and is available under the Apache 2.0 license. With a context length of 32,768 tokens, it supports text-to-text input and output modalities. Mistral Small 3 achieves 81% accuracy on the MMLU benchmark and competes with larger models like Llama 3.3 70B and Qwen 32B, while being three times faster on similar hardware. It's available in both pre-trained and instruction-tuned versions, making it ideal for efficient local deployment.

Use Cases

Here are a few ways teams apply Mistral: Mistral Small 3 (free) in practice—from fast drafting to multimodal understanding. Adapt these ideas to your workflow.

Enhance text analysis speed in applications

Deploy locally for efficient AI tasks

Achieve competitive accuracy in benchmarks

Utilize large context windows in text processing

Key Features

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

24B-parameter language model

Optimized for low-latency performance

Supports text-to-text modalities

32,768 token context length

Apache 2.0 licensed

Pre-trained and instruction-tuned versions

Specs

Overview

Vendor
mistralai

Model ID
mistralai/mistral-small-24b-instruct-2501:free

Release
2025-01-30

Modalities & context

Input
text

Output
text

Context
32,768 tokens

Parameters & defaults

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

Defaults: temperature 0.3, top_p 0.95

Benchmark tests: Mistral: Mistral Small 3 (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

AI has the potential to significantly enhance work, leisure, and creativity in numerous ways. In the workplace, AI can automate repetitive tasks, freeing up employees' time to focus on more strategic and creative endeavors. It can also provide real-time data analysis and insights, aiding in decision-making and improving efficiency. For leisure, AI-powered personal assistants can curate entertainment options tailored to individual preferences, making downtime more enjoyable and productive. AI can also facilitate new forms of social interaction through virtual reality and augmented reality experiences. In the realm of creativity, AI can serve as a collaborative tool, generating ideas, composing music, or even writing stories. It can also provide artists and creators with new mediums and techniques to explore, pushing the boundaries of what is possible. Overall, AI has the potential to transform these aspects of life by augmenting human capabilities and opening up new possibilities.

Run this prompt on Upend.AI

Ready to try Mistral: Mistral Small 3 (free)?

Chat with Mistral: Mistral Small 3

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