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

K EXAONE 2.0 750B A37B NVFP4 by LGAI-EXAONE

 »  All LLMs  »  LGAI-EXAONE  »  K EXAONE 2.0 750B A37B NVFP4   URL Share it on

  38   

K EXAONE 2.0 750B A37B NVFP4 is an open-source language model by LGAI-EXAONE. Features: 750b LLM, VRAM: 399.9GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.39.

  8-bit Base model:lgai-exaone/k-exaon... Base model:quantized:lgai-exao...   Conversational   De   En   Endpoints compatible   Es   Exaone   Exaone moe   Fr   It   Ja   K-exaone   Ko   Lg-ai   Modelopt   Moe   Pl   Pt   Region:us   Safetensors   Sharded   Tensorflow   Vi
Model Card on HF 🤗: https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B-NVFP4 

K EXAONE 2.0 750B A37B NVFP4 Benchmarks

LLME Score: 0.38505
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
K EXAONE 2.0 750B A37B NVFP4 (LGAI-EXAONE/K-EXAONE-2.0-750B-A37B-NVFP4)

K EXAONE 2.0 750B A37B NVFP4 Parameters and Internals

LLM NameK EXAONE 2.0 750B A37B NVFP4
Repository 🤗https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B-NVFP4 
Base Model(s)  LGAI-EXAONE/K-EXAONE-2.0-750B-A37B   LGAI-EXAONE/K-EXAONE-2.0-750B-A37B
Model Size750b
Required VRAM399.9 GB
Updated2026-08-01
MaintainerLGAI-EXAONE
Model Typeexaone_moe
Model Files  10.0 GB: 1-of-53   10.0 GB: 2-of-53   10.0 GB: 3-of-53   10.0 GB: 4-of-53   10.0 GB: 5-of-53   10.0 GB: 6-of-53   10.0 GB: 7-of-53   10.0 GB: 8-of-53   10.0 GB: 9-of-53   10.0 GB: 10-of-53   10.0 GB: 11-of-53   10.0 GB: 12-of-53   10.0 GB: 13-of-53   10.0 GB: 14-of-53   10.0 GB: 15-of-53   10.0 GB: 16-of-53   10.0 GB: 17-of-53   10.0 GB: 18-of-53   10.0 GB: 19-of-53   10.0 GB: 20-of-53   10.0 GB: 21-of-53   10.0 GB: 22-of-53   10.0 GB: 23-of-53   10.0 GB: 24-of-53   10.0 GB: 25-of-53   10.0 GB: 26-of-53   10.0 GB: 27-of-53   10.0 GB: 28-of-53   10.0 GB: 29-of-53   10.0 GB: 30-of-53   10.0 GB: 31-of-53   10.0 GB: 32-of-53   10.0 GB: 33-of-53   10.0 GB: 34-of-53   9.9 GB: 35-of-53   10.0 GB: 36-of-53   10.0 GB: 37-of-53   10.0 GB: 38-of-53   10.0 GB: 39-of-53   10.0 GB: 40-of-53
Supported Languagesen ko es de ja vi fr it pl pt
Model ArchitectureExaoneMoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.9.0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size153600

Best Alternatives to K EXAONE 2.0 750B A37B NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
K EXAONE 2.0 750B A37B FP8256K / 751.3 GB20135
Note: green Score (e.g. "73.2") means that the model is better than LGAI-EXAONE/K-EXAONE-2.0-750B-A37B-NVFP4.

Rank the K EXAONE 2.0 750B A37B NVFP4 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? 55556 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer