Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion parameters.
Instruct model fine-tuned by Mistral. #moe
Modalities
Context
33K
Released
Dec 10, 2023
Knowledge Cutoff
Dec 2023
Token volume and request traffic to this model over time.
Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion parameters. Instruct model fine-tuned by Mistral. #moe
Mixtral 8x7B Instruct has a 32,768 token context window.
Mistral Medium 3.5, Mistral Small 4, Ministral 3 14B 2512 and 15 more are other text models from Mistral AI.
Mixtral 8x7B Instruct was released on December 10, 2023. Its knowledge cutoff is December 31, 2023.