Mistral Large 4 is Mistral's open-weight, general-purpose multimodal model. Its granular Mixture-of-Experts design activates 52B of 1.05T total parameters, with a 1.6B vision encoder handling images.
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.
Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.
Large dataset roleplaying model finetuned for natural response. Made by ReadyArt (Huggingface).
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B. This model is unsloth version of the model.
EM German is a Llama2/Mistral/LeoLM-based model family, finetuned on a large dataset of various instructions in German language. From https://github.com/jphme/EM_German.
This is a 8 bit quantized version of Large Language and Vision Assistant for bio Medicine
Large Language and Vision Assistant for bio Medicine
Large context
Quantized variants of a German large language model (LLM).
I-quants for mistral-large-instruct-2407
IQ2_XSS quant of mistral large 2
The medical LLM published in "Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcare". [Not official distribution]