What are the hardware requirements for EXAONE 3.5 2.4B Instruct?

EXAONE 3.5 2.4B Instruct requires approximately 9.7 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 3.5 2.4B Instruct and how large is it?

EXAONE 3.5 2.4B Instruct is developed by LGAI-EXAONE, a model with 2.4b 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 3.5 2.4B Instruct?

EXAONE 3.5 2.4B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EXAONE 3.5 2.4B Instruct by LGAI-EXAONE — VRAM 9.7GB, 32K context

Name: EXAONE 3.5 2.4B Instruct
Author: LGAI-EXAONE

EXAONE 3.5 2.4B Instruct is an open-source language model by LGAI-EXAONE. Features: 2.4b LLM, VRAM: 9.7GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.3.

Arxiv:2412.04862 Conversational Custom code En Eval-results Exaone Exaone-3.5 Instruct Ko Lg-ai Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct

EXAONE 3.5 2.4B Instruct Parameters and Internals

LLM Name	EXAONE 3.5 2.4B Instruct
Repository 🤗	https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct
Model Size	2.4b
Required VRAM	9.7 GB
Updated	2026-07-18
Maintainer	LGAI-EXAONE
Model Type	exaone
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 4.7 GB: 2-of-2
Supported Languages	en ko
Model Architecture	ExaoneForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.43.0
Tokenizer Class	GPT2Tokenizer
Padding Token	[PAD]
Vocabulary Size	102400
Torch Data Type	float32
Activation Function	silu

Rank the EXAONE 3.5 2.4B Instruct 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 3.5 2.4B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
EXAONE Deep 2.4B	32K / 4.8 GB	1600	101
... 3.5 2.4B Instruct Abliterated	32K / 10.8 GB	112	6