A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length.

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.

Inferor is a merge of top roleplay models, expert on immersive narratives and storytelling.

With 22 billion parameters, Mistral Small v24.09 offers a convenient mid-point between (Mistral NeMo 12B)[/mistralai/mistral-nemo] and (Mistral Large 2)[/mistralai/mistral-large].

This model is currently powered by Mistral-7B-v0.2, and incorporates a "better" fine-tuning thanMistral 7B, inspired by community work.