Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.
Modalities
Context
128K
Released
Oct 17, 2024
Knowledge Cutoff
Sep 2024
Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.
Ministral 8B has a 128,000 token context window.
Mistral Medium 3.5, Mistral Small 4, Ministral 3 14B 2512 and 15 more are other text models from Mistral AI.
Ministral 8B was released on October 17, 2024. Its knowledge cutoff is September 30, 2024.
Token volume and request traffic to this model over time.