ERNIE 4.5 21B A3B Thinking by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  ERNIE 4.5 21B A3B Thinking   URL Share it on

  Autotrain compatible Base model:baidu/ernie-4.5-21b... Base model:finetune:baidu/erni...   Conversational   En   Endpoints compatible   Ernie4.5   Ernie4 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Zh

ERNIE 4.5 21B A3B Thinking Benchmarks

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 Thinking (unsloth/ERNIE-4.5-21B-A3B-Thinking)
๐ŸŒŸ Advertise your project ๐Ÿš€

ERNIE 4.5 21B A3B Thinking Parameters and Internals

LLM NameERNIE 4.5 21B A3B Thinking
Repository ๐Ÿค—https://huggingface.co/unsloth/ERNIE-4.5-21B-A3B-Thinking 
Base Model(s)  baidu/ERNIE-4.5-21B-A3B-Thinking   baidu/ERNIE-4.5-21B-A3B-Thinking
Model Size21b
Required VRAM43.7 GB
Updated2025-09-11
Maintainerunsloth
Model Typeernie4_5_moe
Model Files  5.0 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   5.0 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   5.0 GB: 7-of-9   5.0 GB: 8-of-9   3.7 GB: 9-of-9
Supported Languagesen zh
Model ArchitectureErnie4_5_MoeForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.56.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size103424

Best Alternatives to ERNIE 4.5 21B A3B Thinking

Best Alternatives
Context / RAM
Downloads
Likes
ERNIE 4.5 21B A3B Thinking128K / 43.7 GB32152
ERNIE 4.5 21B A3B PT128K / 44 GB300777135
ERNIE 4.5 21B A3B Base PT128K / 44.3 GB15025823
ERNIE 4.5 21B A3B PT Bf16128K / 43.7 GB371
ERNIE 4.5 21B A3B PT 8bit128K / 23.2 GB322
Note: green Score (e.g. "73.2") means that the model is better than unsloth/ERNIE-4.5-21B-A3B-Thinking.

Rank the ERNIE 4.5 21B A3B Thinking Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51316 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124