Mistral releases its first multimodal model, Pixtral 12B, available on GitHub and Hugging Face, and via API "soon" (Kyle Wiggers/TechCrunch)

French AI startup Mistral has unveiled Pixtral 12B, its first multimodal model capable of processing both images and text, now available on GitHub and Hugging Face. The 12-billion-parameter model, measuring 24GB in size, marks Mistral’s entrance into the field of multimodal AI. An API for Pixtral 12B is expected to be released in the near future, offering users a powerful tool for various applications.

Full Article