Seaweed-7B

Closed weights ByteDance 7B parameters April 2025

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

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
11 April 2025
Authors
Team Seawead, Ceyuan Yang, Zhijie Lin, Yang Zhao, Shanchuan Lin, Zhibei Ma, Haoyuan Guo, Hao Chen, Lu Qi, Sen Wang, Feng Cheng, Feilong Zuo Xuejiao Zeng, Ziyan Yang, Fangyuan Kong, Zhiwu Qing, Fei Xiao, Meng Wei, Tuyen Hoang, Siyu Zhang, Peihao Zhu, Qi Zhao, Jiangqiao Yan, Liangke Gui, Sheng Bi, Jiashi Li, Yuxi Ren, Rui Wang, Huixia Li, Xuefeng Xiao, Shu Liu, Feng Ling, Heng Zhang, Houmin Wei, Hua…

What it does

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

Domain
Video
Task
Video generation, Text-to-video, Image-to-video, Audio generation

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.

Parameters
7B
Training data
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
9 × 10²³ FLOP

989400000000000 FLOP / GPU / sec [H100 reported, bf16 assumed] * 665000 GPU-hours * 3600 sec / hour * 0.38 [reported utilization] = 9.0007697e+23 FLOP

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA H100 SXM5 80GB
Chip-hours
665,000
Hardware utilisation
MFU 38.0%

"Finally, we optimize GPU utilization by implementing fused CUDA kernels to streamline fragmented I/O operations. As a result, Seaweed-7B achieves a Model FLOPs Utilization (MFU) of 38% in distributed training at large-scale."

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
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

How it is classified

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

Record confidence
Confident
Citations
83

Sources

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

Reference
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
Last updated
25 May 2026

What the numbers mean

Where it came from

Seaweed-7B was published by ByteDance, in China, in April 2025. It comes out of industry.

It works in Video, and is recorded as doing video generation, Text-to-video, Image-to-video, Audio generation.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

Training it took roughly 9 × 10²³ FLOP of computation, on NVIDIA H100 SXM5 80GB — a measure of what producing the model cost, not of how fast it answers.

Answers

Seaweed-7B — common questions

01

How many parameters does Seaweed-7B have?

Seaweed-7B has 7B parameters. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

02

Who created Seaweed-7B?

Seaweed-7B was published by ByteDance, based in China, categorised as industry.

03

When was Seaweed-7B released?

Seaweed-7B was published in April 2025.

04

What is Seaweed-7B used for?

Seaweed-7B works in Video, and is recorded as handling video generation, Text-to-video, Image-to-video, Audio generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

05

How much compute was used to train Seaweed-7B?

Around 9 × 10²³ FLOP, on NVIDIA H100 SXM5 80GB. 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.

06

What GPU do I need to run Seaweed-7B?

None. Seaweed-7B is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

07

Is Seaweed-7B open source?

No. Seaweed-7B has not had its weights published, so it exists only as a service controlled by its owner.

Source

Original publication

Record last updated 25 May 2026

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.