DeepSeek V4 Pro is Live → Try it now.

Model Library/Mistral/Mixtral MoE 8x7B Instruct (HF version)
Mistral Logo Icon

Mixtral MoE 8x7B Instruct (HF version)

Ready
Deploy on Demand
accounts/fireworks/models/mixtral-8x7b-instruct-hf

    Mixtral MoE 8x7B Instruct (HF Version) is the original, FP16 version of Mixtral MoE 8x7B Instruct whose results should be consistent with the official Hugging Face implementation.

    Mixtral MoE 8x7B Instruct (HF version) API Features

    On-demand Deployment

    Docs

    On-demand deployments allow you to use Mixtral MoE 8x7B Instruct (HF version) on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    2/6/2024
    Kind
    Base model
    Provider
    Mistral
    Hugging Face
    mistralai/Mixtral-8x7B-Instruct-v0.1

    Specification

    Calibrated
    No
    Mixture-of-Experts
    Yes
    Parameters
    46.7B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Context Length
    32.7k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported