Pixtral Large: Advanced Multimodal AI Model
Product Introduction
Pixtral Large is a cutting-edge multimodal AI model introduced by Mistral AI, built upon Mistral Large 2. It features advanced image understanding capabilities, enabling comprehension of documents, charts, and natural images while retaining Mistral Large 2's leadership in text understanding. The model is available under the Mistral Research License (MRL) for research and educational purposes and the Mistral Commercial License for commercial use.
Key Features
- Multimodal Performance: Capable of understanding documents, charts, and natural images.
- Leading Text Understanding: Maintains the text understanding capabilities of Mistral Large 2.
- Model Size: 123B multimodal decoder with a 1B parameter visual encoder.
- Context Window: Supports a 128K context window suitable for high-resolution images.
- Multilingual OCR and Inference: Capable of processing multilingual inputs and performing reasoning.
- Chart Understanding: Able to analyze charts and provide accurate interpretations.
Enterprise-grade Applications: Suitable for knowledge exploration.
Product Data
- Performance Benchmarks: Surpassed models in tests such as MathVista, ChartQA, and DocVQA.
- Commercial and Research Licensing: Available under Mistral Research License (MRL) and Mistral Commercial License. ## Product Link
Pixtral Large Official Website
