What are the hardware requirements for EXAONE 4.0 32B?

EXAONE 4.0 32B requires approximately 63.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed EXAONE 4.0 32B and how large is it?

EXAONE 4.0 32B is developed by LGAI-EXAONE, a model with 32b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate EXAONE 4.0 32B?

EXAONE 4.0 32B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EXAONE 4.0 32B by LGAI-EXAONE — VRAM 63.7GB, 128K context

Name: EXAONE 4.0 32B
Author: LGAI-EXAONE

EXAONE 4.0 32B is an open-source language model by LGAI-EXAONE. Features: 32b LLM, VRAM: 63.7GB, Context: 128K, License: other, LLM Explorer Score: 0.26.

Arxiv:2507.11407 Conversational En Endpoints compatible Es Exaone Exaone-4.0 Exaone4 Ko Lg-ai Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B

EXAONE 4.0 32B Parameters and Internals

LLM Name	EXAONE 4.0 32B
Repository 🤗	https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B
Model Size	32b
Required VRAM	63.7 GB
Updated	2026-06-15
Maintainer	LGAI-EXAONE
Model Type	exaone4
Model Files	5.0 GB: 1-of-14 4.9 GB: 2-of-14 4.8 GB: 3-of-14 4.8 GB: 4-of-14 4.8 GB: 5-of-14 4.8 GB: 6-of-14 4.8 GB: 7-of-14 4.8 GB: 8-of-14 4.8 GB: 9-of-14 4.8 GB: 10-of-14 4.8 GB: 11-of-14 4.8 GB: 12-of-14 4.7 GB: 13-of-14 1.1 GB: 14-of-14
Supported Languages	en ko es
Model Architecture	Exaone4ForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.54.0
Tokenizer Class	GPT2Tokenizer
Padding Token	[PAD]
Vocabulary Size	102400
Torch Data Type	bfloat16
Errors	replace

Rank the EXAONE 4.0 32B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Quantized Models of the EXAONE 4.0 32B

Model	Likes	Downloads	VRAM
EXAONE 4.0 32B 4bit	2	87	18 GB

Best Alternatives to EXAONE 4.0 32B

Best Alternatives	Context / RAM	Downloads	Likes
EXAONE 4.0.1 32B	128K / 63.7 GB	5938	27
EXAONE 4.0 32B	128K / 63.7 GB	12	2
...hui EXAONE 4.0 32B Abliterated	128K / 63.7 GB	166	0
EXAONE 4.0 32B 4bit	128K / 18 GB	87	2