Emu2 by BAAI

 ยป  All LLMs  ยป  BAAI  ยป  Emu2   URL Share it on

Emu2 is an open-source language model by BAAI. Features: LLM, VRAM: 148GB, Context: 2K, LLM Explorer Score: 0.12.

  Arxiv:2312.13286   Custom code   En   Pytorch   Region:us   Sharded
Model Card on HF ๐Ÿค—: https://huggingface.co/BAAI/Emu2 

Emu2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Emu2 (BAAI/Emu2)
๐ŸŒŸ Advertise your project ๐Ÿš€

Emu2 Parameters and Internals

Model Type 
Generative Multimodal Model
Additional Notes 
Emu2 exhibits strong multimodal in-context learning abilities and can solve tasks requiring on-the-fly reasoning through visual prompting and object-grounded generation.
Supported Languages 
en (High proficiency)
Training Details 
Data Sources:
Large-scale multimodal sequences
Methodology:
Unified autoregressive objective
Input Output 
Input Format:
Interleaved image and textual prompts
Accepted Modalities:
Text, Image
Output Format:
Textual descriptions or responses based on input prompts.
Performance Tips:
Ensure the GPU has sufficient memory to load the model for optimal performance.
LLM NameEmu2
Repository ๐Ÿค—https://huggingface.co/BAAI/Emu2 
Required VRAM148 GB
Updated2026-03-22
MaintainerBAAI
Model Files  9.9 GB: 1-of-15   10.0 GB: 2-of-15   9.8 GB: 3-of-15   10.0 GB: 4-of-15   9.8 GB: 5-of-15   9.9 GB: 6-of-15   9.9 GB: 7-of-15   9.8 GB: 8-of-15   10.0 GB: 9-of-15   9.8 GB: 10-of-15   9.9 GB: 11-of-15   9.9 GB: 12-of-15   9.8 GB: 13-of-15   10.0 GB: 14-of-15   9.5 GB: 15-of-15
Supported Languagesen
Model ArchitectureEmuForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32272
Torch Data Typefloat32

Best Alternatives to Emu2

Best Alternatives
Context / RAM
Downloads
Likes
Emu2 Chat2K / 148 GB5929

Rank the Emu2 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? 52509 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a