ER

ERNIE-4.5-21B-A3B-Base

Foundation modelERNIE-4.5

ERNIE-4.5-21B-A3B-Base

Release date: 2025-06-30Updated: 2025-06-30 10:53:12865
Parameters
21B
Context length
128K
Chinese support
Supported
Reasoning ability

ERNIE-4.5-21B-A3B-Base is an AI model published by 百度, released on 2025-06-30, for Foundation model, with 21B parameters, and 128K context length, requiring about 44.16 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-4.5-21B-A3B-Base

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
32K tokens
Model type
Foundation model
Modality (in / out)
Text → Text
Release date
2025-06-30
Model file size
44.16 GB
MoE architecture
Yes
Total params / Active params
21B / 3B
Knowledge cutoff
No data
ERNIE-4.5-21B-A3B-Base

Open source & experience

Code license
Weights license
Apache 2.0- 免费商用授权
GitHub repo
GitHub link unavailable
ERNIE-4.5-21B-A3B-Base

Official resources

Paper
No paper available
DataLearnerAI blog
No blog post yet
ERNIE-4.5-21B-A3B-Base

API details

API speed
3/5
No public API pricing yet.
ERNIE-4.5-21B-A3B-Base

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

ERNIE-4.5-21B-A3B-Base

Publisher

ERNIE-4.5-21B-A3B-Base

Model Overview

ERNIE-4.5-21B-A3B-Base is an AI model published by 百度, released on 2025-06-30, for Foundation model, with 21B parameters, and 128K context length, requiring about 44.16 GB storage, under the Apache 2.0 license.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code