• LLM TrustAI Model Discovery
Platform
  • Home
  • Models
  • Categories
  • Compare
  • Blog
  • Newsletter
My Account
  • Dashboard
Categories
    Back to Models

    Mixtral 8x22B

    141B

    Sparse mixture-of-experts model with 141B total / 39B active parameters. Outstanding efficiency.

    open-sourcemoeefficientapache-2.0code
    Architecture

    mistral

    Parameters

    141B

    Context Length

    65,536 tokens

    License

    Apache 2.0

    About Mixtral 8x22B

    Mixtral 8x22B uses a sparse MoE architecture with 8 experts, activating only 2 per token. This provides the quality of a much larger model with the speed of a smaller one.

    Author

    Community

    Category

    text generation

    Downloads

    1,876,543

    License

    Apache 2.0