What are the hardware requirements for EXAONE Deep 32B?

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

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

EXAONE Deep 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 Deep 32B?

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

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

Name: EXAONE Deep 32B
Author: LGAI-EXAONE

EXAONE Deep 32B is an open-source language model by LGAI-EXAONE. Features: 32b LLM, VRAM: 63.7GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.2.

Arxiv:2503.12524 Base model:finetune:lgai-exaon... Base model:lgai-exaone/exaone-... Conversational Custom code En Exaone Exaone-deep Instruct Ko Lg-ai Region:us Safetensors Sharded Tensorflow

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

EXAONE Deep 32B Parameters and Internals

LLM Name	EXAONE Deep 32B
Repository 🤗	https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-32B
Base Model(s)	LGAI-EXAONE/EXAONE-3.5-32B-Instruct LGAI-EXAONE/EXAONE-3.5-32B-Instruct
Model Size	32b
Required VRAM	63.7 GB
Updated	2026-07-16
Maintainer	LGAI-EXAONE
Model Type	exaone
Instruction-Based	Yes
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
Model Architecture	ExaoneForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.43.1
Tokenizer Class	GPT2Tokenizer
Padding Token	[PAD]
Vocabulary Size	102400
Torch Data Type	bfloat16
Activation Function	silu

Rank the EXAONE Deep 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

Best Alternatives to EXAONE Deep 32B

Best Alternatives	Context / RAM	Downloads	Likes
EXAONE 3.5 32B Instruct	32K / 128.3 GB	60307	130
...E 3.5 32B Instruct Abliterated	32K / 63.7 GB	117	6

Note: green Score (e.g. "73.2") means that the model is better than LGAI-EXAONE/EXAONE-Deep-32B.