Mixtral-8x22B-Instruct-v0.1 is an open-weight Mixture-of-Experts model with 141B total parameters (39B active). It is designed for instruction following and outperforms many larger dense models. The model is available on Hugging Face for local or hosted inference.
Mixtral 8x22B Instruct is a Foundation models & chat product. It focuses on accessing high-performance open language models without relying on closed commercial APIs. Mixtral 8x22B Instruct is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
It is developed by Mistral AI (France), and the product first shipped in 2024. The project is developed in the open on GitHub with 922 stars and 30 commits in the last 90 days. Among its 4 catalogued features are mixture-of-Experts, instruction tuned, and large context.
Latest indexed changes and source events
mistralai/Mixtral-8x22B-Instruct-v0.1 verified by the PulseGate indexer
