ERNIE 4.0

Closed weights Baidu October 2023

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
Baidu
Organisation type
Industry
Country
China
Published
17 October 2023

What it does

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

Domain
Multimodal, Language, Video, Image generation
Task
Chat, Language modeling/generation, Video generation, Image 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.

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
API access
Training code
Unreleased

"ERNIE 4.0 is now accessible to invited users on ERNIE Bot, and the API will be available upon application to enterprise clients via Qianfan foundation model platform."

How it is classified

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

Foundation model
Yes
Likely above 10²³ FLOP
Yes
Why it is tracked
Significant use

Likely SOTA for Mandarin? But very little info available. Lots of users (https://www.cnn.com/2023/12/15/tech/gpt4-china-baidu-ernie-ai-comparison-intl-hnk/index.html): "Baidu says ERNIE has racked up 70 million users. That’s compared with 150 million users for ChatGPT, according to an estimate from Similarweb, a digital data and analytics company."

Record confidence
Unknown

Sources

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

Reference
Baidu Launches ERNIE 4.0 Foundation Model, Leading a New Wave of AI-Native Applications
Last updated
28 November 2025

What the numbers mean

Background

ERNIE 4.0 was published by Baidu, in China, in October 2023. The organisation is categorised as industry.

It works in Multimodal, Language, Video, Image generation, and is recorded as doing chat, Language modeling/generation, Video generation, Image 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

Its inclusion criterion is significant use.

Answers

ERNIE 4.0 — common questions

01

How many parameters does ERNIE 4.0 have?

No parameter count has been published for ERNIE 4.0, which is why no memory or speed figure appears on this page.

02

Who created ERNIE 4.0?

ERNIE 4.0 was published by Baidu, based in China, categorised as industry.

03

When was ERNIE 4.0 released?

ERNIE 4.0 was published in October 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is ERNIE 4.0 used for?

ERNIE 4.0 works in Multimodal, Language, Video, Image generation, and is recorded as handling chat, Language modeling/generation, Video generation, Image generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

05

What GPU do I need to run ERNIE 4.0?

None. ERNIE 4.0 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.

06

Is ERNIE 4.0 open source?

No. ERNIE 4.0 has not had its weights published, so it exists only as a service controlled by its owner.

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.