1. Tutorial Introduction

Ministral-3-14B-Instruct-2512 is a multimodal model released by Mistral AI in December 2025. It supports multimodal (text and image) and multilingual capabilities, offering high performance and cost-effectiveness. Mistral 3, combined with optimization technologies from partners like NVIDIA, can run efficiently on various hardware platforms and is suitable for edge computing, enterprise deployments, and other scenarios, providing developers with powerful tools to build and deploy AI applications.

This tutorial uses a dual-card RTX 5090 setup.

2. Project Examples

3. Operation steps

1. After starting the container, click the API address to enter the Web interface

2. Usage steps

If "Bad Gateway" is displayed, it means the model is initializing. Since the model is large, please wait about 2-3 minutes and refresh the page.