Baichuan-Omni

Closed weights Baichuan,Westlake University,Zhejiang University (ZJU) 7B parameters October 2024

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
Baichuan,Westlake University,Zhejiang University (ZJU)
Organisation type
Industry,Academia,Academia
Country
China
Published
11 October 2024
Authors
Yadong Li, Haoze Sun, Mingan Lin, Tianpeng Li, Guosheng Dong, Tao Zhang, Bowen Ding, Wei Song, Zhenglin Cheng, Yuqi Huo, Song Chen, Xu Li, Da Pan, Shusen Zhang, Xin Wu, Zheng Liang, Jun Liu, Tao Zhang, Keer Lu, Yaqi Zhao, Yanjun Shen, Fan Yang, Kaicheng Yu, Tao Lin, Jianhua Xu, Zenan Zhou

What it does

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

Domain
Language, Vision, Multimodal, Audio, Speech, Video
Task
Visual question answering, Language modeling/generation, Video description, Speech synthesis, Image captioning

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

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

code and weights are supposed to be here, but not yet: https://github.com/westlake-baichuan-mllm/bc-omni?tab=readme-ov-file

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
35

Sources

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

Reference
Baichuan-Omni Technical Report
Last updated
25 May 2026

What the numbers mean

Background

Baichuan-Omni was published by Baichuan,Westlake University,Zhejiang University (ZJU), in China, in October 2024. The organisation is categorised as industry,Academia,Academia.

It works in Language, Vision, Multimodal, Audio, Speech, Video, and is recorded as doing visual question answering, Language modeling/generation, Video description, Speech synthesis, Image captioning.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Answers

Baichuan-Omni — common questions

01

Is Baichuan-Omni open source?

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

02

How many parameters does Baichuan-Omni have?

Baichuan-Omni 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.

03

Who created Baichuan-Omni?

Baichuan-Omni was published by Baichuan,Westlake University,Zhejiang University (ZJU), based in China, categorised as industry,Academia,Academia.

04

When was Baichuan-Omni released?

Baichuan-Omni was published in October 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Baichuan-Omni used for?

Baichuan-Omni works in Language, Vision, Multimodal, Audio, Speech, Video, and is recorded as handling visual question answering, Language modeling/generation, Video description, Speech synthesis, Image captioning. 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.

06

What GPU do I need to run Baichuan-Omni?

None. Baichuan-Omni 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.

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.