DeepSeek V4 Pro is Live → Try it now.

Model Library/Deepseek/DeepSeek R1 Distill Llama 70B
Deepseek Logo Mark

DeepSeek R1 Distill Llama 70B

Ready
Deploy on Demand
Fine-tune
accounts/fireworks/models/deepseek-r1-distill-llama-70b

    Llama 70B distilled with reasoning from Deepseek R1

    DeepSeek R1 Distill Llama 70B API Features

    Fine-tuning

    Docs

    DeepSeek R1 Distill Llama 70B can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

    On-demand Deployment

    Docs

    On-demand deployments allow you to use DeepSeek R1 Distill Llama 70B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Metadata

    State
    Ready
    Created on
    1/21/2025
    Kind
    Base model
    Provider
    Deepseek
    Hugging Face
    deepseek-ai/DeepSeek-R1-Distill-Llama-70B

    Specification

    Calibrated
    Yes
    Mixture-of-Experts
    No
    Parameters
    70.5B

    Supported Functionality

    Fine-tuning
    Supported
    Serverless
    Not supported
    Context Length
    131k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported