ERNIE-4.5-VL-424B-A47B-Base

多模态大模型

Release date: 2025-06-30更新于: 2025-06-30 10:21:27871

Live demoGitHubHugging Face Compare

Parameters

4240.0亿

Context length

128K

Chinese support

Supported

Reasoning ability

ERNIE-4.5-VL-424B-A47B-Base is an AI model published by 百度, released on 2025-06-30, for 多模态大模型, with 4240.0B parameters, and 128K tokens context length, requiring about 717.95 GB storage, under the Apache 2.0 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

ERNIE-4.5-VL-424B-A47B-Base

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

32768 tokens

Model type

多模态大模型

Release date

2025-06-30

Model file size

717.95 GB

MoE architecture

Yes

Total params / Active params

4240.0B / 470B

Knowledge cutoff

No data

ERNIE-4.5-VL-424B-A47B-Base

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

GitHub link unavailable

Hugging Face

https://huggingface.co/baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle

Live demo

https://yiyan.baidu.com/

ERNIE-4.5-VL-424B-A47B-Base

Official resources

Paper

No paper available

DataLearnerAI blog

No blog post yet

ERNIE-4.5-VL-424B-A47B-Base

API details

API speed

2/5

No public API pricing yet.

ERNIE-4.5-VL-424B-A47B-Base

Benchmark Results

ERNIE-4.5-VL-424B-A47B-Base currently shows benchmark results led by GPQA Diamond (79 / 166, score 76.80), MMMU (22 / 28, score 70), LiveCodeBench (90 / 109, score 38.80). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.