Seed-OSS-36B-Base

Open weights ByteDance August 2025

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
ByteDance
Organisation type
Industry
Country
China
Published
21 August 2025

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Language modeling/generation, Question answering, System control, Code generation, Mathematical reasoning

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
12,000,000,000,000 tokens

"Trained with 12T tokens"

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
2.6 × 10²⁴ FLOP

6 FLOP / parameter / token * 36 * 10^9 parameters * 12 * 10^12 tokens = 2.592e+24 FLOP

How it was established
Operation counting

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Open — downloadable
Model access
Open weights (unrestricted)
Training code
Unreleased

Apache 2.0 https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Base

Hugging Face
ByteDance-Seed

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Seed-OSS Open-Source Models Release
Last updated
28 November 2025

What the numbers mean

Background

Seed-OSS-36B-Base was published by ByteDance, in China, in August 2025. The organisation is categorised as industry.

It works in Language, and is recorded as doing language modeling/generation, Question answering, System control, Code generation, Mathematical reasoning.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the ByteDance-Seed organisation on Hugging Face.

How it was trained

Producing it required around 2.6 × 10²⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

The training set ran to roughly 12,000,000,000,000 tokens.

Answers

Seed-OSS-36B-Base — common questions

01

Where can I download Seed-OSS-36B-Base?

Its weights are published under the ByteDance-Seed organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

02

How much compute was used to train Seed-OSS-36B-Base?

Around 2.6 × 10²⁴ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

03

What GPU do I need to run Seed-OSS-36B-Base?

We cannot say. Seed-OSS-36B-Base has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

04

Is Seed-OSS-36B-Base open source?

Its weights are published, so Seed-OSS-36B-Base can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

05

How many parameters does Seed-OSS-36B-Base have?

No parameter count has been published for Seed-OSS-36B-Base, which is why no memory or speed figure appears on this page.

06

Who created Seed-OSS-36B-Base?

Seed-OSS-36B-Base was published by ByteDance, based in China, categorised as industry.

07

When was Seed-OSS-36B-Base released?

Seed-OSS-36B-Base was published in August 2025.

08

What is Seed-OSS-36B-Base used for?

Seed-OSS-36B-Base works in Language, and is recorded as handling language modeling/generation, Question answering, System control, Code generation, Mathematical reasoning. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.