Pixtral 12B 24.09

Pixtral is a 12-billion-parameter multimodal model by Mistral AI, combining a 12B-parameter text decoder with a 400M-parameter vision encoder. It processes interleaved text and images natively, supporting variable image sizes and a 128K-token context window.

Features

Variable image support

Multilingual

Apache 2.0 license

Vision-to-code

Details

Price

Free

Source

Open Source

Need A Custom
AI Agent?

Let's build tailored AI agents designed to match your unique workflows, goals, and business needs — just drop us a line.

Request

Need A Custom
AI Agent?

Let's build tailored AI agents designed to match your unique workflows, goals, and business needs — just drop us a line.

Request

Need A Custom AI Agent?

Let's build tailored AI agents designed to match your unique workflows, goals, and business needs — just drop us a line.

Request

Need A Custom AI Agent?

Let's build tailored AI agents designed to match your unique workflows, goals, and business needs — just drop us a line.

Request