Fireworks RFT now available! Fine-tune open models that outperform frontier models. Try today

Model Library
/Fireworks AI/Seed OSS 36B Instruct
Fireworks Logo Mark

Seed OSS 36B Instruct

Ready
fireworks/seed-oss-36b-instruct

    Seed-OSS is a series of open-source large language models developed by ByteDance's Seed Team, designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features. Although trained with only 12T tokens, Seed-OSS achieves excellent performance on several popular open benchmarks.

    Seed OSS 36B Instruct API Features

    On-demand Deployment

    Docs

    On-demand deployments give you dedicated GPUs for Seed OSS 36B Instruct using Fireworks' reliable, high-performance system with no rate limits.

    Metadata

    State
    Ready
    Created on
    12/11/2025
    Kind
    Base model
    Provider
    Fireworks AI
    Hugging Face
    Seed-OSS-36B-Instruct

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    36B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Not supported
    Serverless LoRA
    Not supported
    Context Length
    524.3k tokens
    Function Calling
    Supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported