m-polignano/ANITA-NEXT-24B-Magistral-2506-VISION-ITA

ANITA-NEXT-24B-Magistral-2506-VISION-ITA by m-polignano is a 24 billion parameter Thinking Vision Language Model built on the Mistral architecture. It merges textual layers from ANITA-NEXT-24B-Magistral-2506-ITA with vision layers from mistralai/Mistral-Small-3.1-24B-Instruct-2503. This multilingual model supports both English and Italian, with a focus on further fine-tuning for specific Italian tasks, and has a context length of 128k, degrading after 40k.