Pixtral Large
Mistral AI · November 2024
● activeOpen Weightdecoder onlymultimodal
Parameters124B
Context Window128K tokens
Description
Mistral's 124-billion-parameter open-weight multimodal model that combines strong language capabilities with advanced vision understanding. Features a 128K context window and can process both text and images natively, positioning it as a competitive open alternative to GPT-4V and Gemini.
Key Innovations
Multimodal
MultimodalProcessing multiple types of input (text, images, audio, video) in a single model.
Open Weight
Open WeightModel weights are publicly released but training data/code may not be. Enables fine-tuning but not full reproduction.