Oct 28, 26
Oct 28, 26
Introducing Mistral Large 4 on Dell Enterprise Hub
Mistral Large 4 is a multimodal, multilingual Mixture-of-Experts model from Mistral. It takes text and images as input and generates text, with 1.05T total parameters, 49B active parameters per token (52B including embeddings and output layers), and a context window of 1M tokens. Today, we are releasing both FP8 and NVFP4 variants to the catalog.
Deploy Mistral Large 4 FP8 → · Deploy Mistral Large 4 NVFP4 →