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

EXAONE 3.5 32B Instruct by LGAI-EXAONE

 »  All LLMs  »  LGAI-EXAONE  »  EXAONE 3.5 32B Instruct   URL Share it on

  20327   

EXAONE 3.5 32B Instruct is an open-source language model by LGAI-EXAONE. Features: 32b LLM, VRAM: 128.3GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.34.

  Arxiv:2412.04862   Conversational   Custom code   En   Exaone   Exaone-3.5   Instruct   Ko   Lg-ai   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-32B-Instruct 

EXAONE 3.5 32B Instruct Benchmarks

MMLU Pro: 40.41
GPQA: 5.03
MUSR: 5.15
BBH: 39.82
IFEval: 83.92 vs 88 (so35)-4.6%
MATH Lvl 5: 51.28
LLME Score: 0.34357
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
EXAONE 3.5 32B Instruct (LGAI-EXAONE/EXAONE-3.5-32B-Instruct)
🌟 Advertise your project 🚀

EXAONE 3.5 32B Instruct Parameters and Internals

LLM NameEXAONE 3.5 32B Instruct
Repository 🤗https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-32B-Instruct 
Model Size32b
Required VRAM128.3 GB
Updated2026-03-29
MaintainerLGAI-EXAONE
Model Typeexaone
Instruction-BasedYes
Model Files  4.8 GB: 1-of-27   5.0 GB: 2-of-27   4.7 GB: 3-of-27   5.0 GB: 4-of-27   4.7 GB: 5-of-27   5.0 GB: 6-of-27   4.7 GB: 7-of-27   5.0 GB: 8-of-27   4.7 GB: 9-of-27   5.0 GB: 10-of-27   4.7 GB: 11-of-27   5.0 GB: 12-of-27   4.7 GB: 13-of-27   5.0 GB: 14-of-27   4.7 GB: 15-of-27   5.0 GB: 16-of-27   4.7 GB: 17-of-27   5.0 GB: 18-of-27   4.7 GB: 19-of-27   5.0 GB: 20-of-27   4.7 GB: 21-of-27   5.0 GB: 22-of-27   4.7 GB: 23-of-27   5.0 GB: 24-of-27   4.7 GB: 25-of-27   5.0 GB: 26-of-27   2.1 GB: 27-of-27
Supported Languagesen ko
Model ArchitectureExaoneForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.43.0
Tokenizer ClassGPT2Tokenizer
Padding Token[PAD]
Vocabulary Size102400
Torch Data Typefloat32
Activation Functionsilu

Best Alternatives to EXAONE 3.5 32B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
EXAONE Deep 32B32K / 63.7 GB365300
...E 3.5 32B Instruct Abliterated32K / 63.7 GB1176

Rank the EXAONE 3.5 32B Instruct 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? 53053 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer