LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

ERNIE 4.5 21B A3B PT by baidu

 »  All LLMs  »  baidu  »  ERNIE 4.5 21B A3B PT   URL Share it on

  167628   
  Autotrain compatible   Conversational   En   Endpoints compatible   Ernie4.5   Ernie4 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT 

ERNIE 4.5 21B A3B PT Benchmarks

LLME Score: 0.38064
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ERNIE 4.5 21B A3B PT (baidu/ERNIE-4.5-21B-A3B-PT)
🌟 Advertise your project 🚀

ERNIE 4.5 21B A3B PT Parameters and Internals

LLM NameERNIE 4.5 21B A3B PT
Repository 🤗https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-PT 
Model Size21b
Required VRAM44 GB
Updated2025-09-23
Maintainerbaidu
Model Typeernie4_5_moe
Model Files  4.2 GB: 1-of-11   4.2 GB: 2-of-11   4.2 GB: 3-of-11   4.2 GB: 4-of-11   4.2 GB: 5-of-11   4.2 GB: 6-of-11   4.2 GB: 7-of-11   4.2 GB: 8-of-11   4.2 GB: 9-of-11   4.2 GB: 10-of-11   2.0 GB: 11-of-11
Supported Languagesen zh
Model ArchitectureErnie4_5_MoeForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.54.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size103424
Torch Data Typebfloat16

Quantized Models of the ERNIE 4.5 21B A3B PT

Model
Likes
Downloads
VRAM
ERNIE 4.5 21B A3B PT 8bit23723 GB

Best Alternatives to ERNIE 4.5 21B A3B PT

Best Alternatives
Context / RAM
Downloads
Likes
ERNIE 4.5 21B A3B Thinking128K / 43.7 GB136195736
ERNIE 4.5 21B A3B Base PT128K / 44.3 GB157225
ERNIE 4.5 21B A3B Thinking128K / 43.7 GB1507
ERNIE 4.5 21B A3B PT Bf16128K / 43.7 GB381
ERNIE 4.5 21B A3B PT 8bit128K / 23.2 GB372
Note: green Score (e.g. "73.2") means that the model is better than baidu/ERNIE-4.5-21B-A3B-PT.

Rank the ERNIE 4.5 21B A3B PT Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51545 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer