Get the latest tech news

Mistral Releases Pixtral 12B, Its First-Ever Multimodal AI Model


Mistral AI has launched Pixtral 12B, its first multimodal model with language and vision processing capabilities, positioning it to compete with AI leaders like OpenAI and Anthropic. You can download its source code from Hugging Face, GitHub, or via a torrent link. VentureBeat reports: While the of...

VentureBeat reports: While the official details of the new model, including the data it was trained upon, remain under wraps, the core idea appears that Pixtral 12B will allow users to analyze images while combining text prompts with them. The move is a first for Mistral, but it is important to note that multiple other models, including those from competitors like OpenAI and Anthropic, already have image-processing capabilities. As shared by initial testers on X, the 24GB model's architecture appears to have 40 layers, 14,336 hidden dimension sizes and 32 attention heads for extensive computational processing.

Get the Android app

Or read this on Slashdot

Read more on:

Photo of model

model

Photo of mistral releases

mistral releases

Photo of pixtral 12b

pixtral 12b

Related news:

News photo

Is telling a model to "not hallucinate" absurd?

News photo

PlayStation’s Astro Bot Is a Model for the Video-Game Industry

News photo

Have we stopped to think about what LLMs model?