What are the hardware requirements for EXAONE Deep 7.8B?

EXAONE Deep 7.8B requires approximately 15.6 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 7.8B and how large is it?

EXAONE Deep 7.8B is developed by LGAI-EXAONE, a model with 7.8b 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 7.8B?

EXAONE Deep 7.8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EXAONE Deep 7.8B by LGAI-EXAONE — VRAM 15.6GB, 32K context

Name: EXAONE Deep 7.8B
Author: LGAI-EXAONE

EXAONE Deep 7.8B is an open-source language model by LGAI-EXAONE. Features: 7.8b LLM, VRAM: 15.6GB, 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-7.8B

EXAONE Deep 7.8B Parameters and Internals

LLM Name	EXAONE Deep 7.8B
Repository 🤗	https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-7.8B
Base Model(s)	LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct
Model Size	7.8b
Required VRAM	15.6 GB
Updated	2026-07-20
Maintainer	LGAI-EXAONE
Model Type	exaone
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-4 4.9 GB: 2-of-4 4.9 GB: 3-of-4 0.8 GB: 4-of-4
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 7.8B 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 7.8B

Best Alternatives	Context / RAM	Downloads	Likes
EXAONE 3.5 7.8B Instruct	32K / 31.2 GB	515747	159
... 3.5 7.8B Instruct Abliterated	32K / 31.2 GB	153	6
EXAONE 3.5 7.8B Instruct AWQ	32K / 5.3 GB	485551	18

Note: green Score (e.g. "73.2") means that the model is better than LGAI-EXAONE/EXAONE-Deep-7.8B.