ERNIE 4.5 21B A3B PT

Name: ERNIE 4.5 21B A3B PT
Author: Baidu

by BaiduERNIE

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released July 2025131K context≈ 98,304 words21B params

ERNIE 4.5 21B A3B PT is a sparse mixture-of-experts model from Baidu that activates only 3 billion parameters at a time despite having 21 billion total, keeping inference costs low while preserving a broad knowledge base. It handles long contexts up to 128K tokens and shows particular strength in Chinese-language tasks, reflecting Baidu's deep investment in that linguistic domain.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Long Context

Moderate

Factual Knowledge

ERNIE 4.5 21B A3B PT

by BaiduERNIE

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released July 2025131K context≈ 98,304 words21B params

ERNIE 4.5 21B A3B PT is a sparse mixture-of-experts model from Baidu that activates only 3 billion parameters at a time despite having 21 billion total, keeping inference costs low while preserving a broad knowledge base. It handles long contexts up to 128K tokens and shows particular strength in Chinese-language tasks, reflecting Baidu's deep investment in that linguistic domain.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Long Context

Moderate

Factual Knowledge

Glossary

InferenceThe process of running a trained model to generate predictions or outputs from new inputs.Knowledge BaseA structured or unstructured collection of documents and facts that a system retrieves from to answer queries.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.TokensThe basic units of text that a language model processes, typically representing words or word fragments.

Capabilities

Capabilities

Use Case Fit

Glossary