Pixtral Large
Mistral AI released the 多模态 model · Launched on 2024-11
Open Source
多模态
开源
API 可用
模型简介
Pixtral Large is Mistral AI's flagship vision-language model, based on the Mistral Large 2 architecture with a new advanced vision encoder. It excels in document understanding, chart analysis, and multimodal reasoning, supporting a 128K token context and multilingual processing. Pixtral Large is a leader among open-source vision-language models and can handle complex mixed text-image tasks.
核心特性
- 124B 参数视觉语言模型
- 128K 上下文
- 文档图表分析
- 多语言支持
核心优势
- 视觉理解能力领先
- 开源灵活
- 文档分析出色
技术规格
参数量
124B
上下文窗口
128K tokens
API 支持
Yes
开源状态
Open Source
发布日期
2024-11
提供商
Mistral AI
价格信息
免费开源；API 按量付费
基准测试
MMMU 62.0%, MathVista 72.5%, 开源 VLM 领先