LG AI Research · Open-Weight Models

EXAONE 3.5

Name: EXAONE 3.5
Author: LG AI Research

LG AI Research's bilingual English-Korean models in 2.4B, 7.8B and 32B sizes with 32K context.

Run it locally

With Ollama installed, download and start the default version with:

ollama run exaone3.5:7.8b

Variant	Download
exaone3.5:7.8b	4.8GB
exaone3.5:2.4b	1.6GB
exaone3.5:32b	19GB

Memory: About 4.8GB for the default exaone3.5:7.8b version (4-bit)
Formats: Safetensors (Hugging Face), GGUF (Ollama, llama.cpp, LM Studio)

The download size is roughly the memory (RAM or GPU VRAM) needed to load a variant; allow extra for long contexts. See our hardware guide.

Overview

EXAONE 3.5 is LG’s open model family, with particular strength in Korean alongside English and long-context tasks.

Highlights

2.4B, 7.8B and 32B sizes
English and Korean
32K-token context window
Strong long-context results for its size

Typical uses

Korean-English assistants and research.

Things to consider

Non-commercial license.
Download sizes refer to the default quantized versions in the Ollama library; full-precision weights are larger.

Specifications are taken from the model card on Hugging Face, the Ollama library and the provider’s announcement. Benchmark results depend on evaluation settings; see how AI benchmarks work.

#Open Weight Models #Open Weights #Local AI #LG AI Research

Similar models

View all

CohereOct 24, 2024

Aya Expanse

Cohere For AI's multilingual research models covering 23 languages, built to close the quality gap between English and other languages.

Type: Open-Weight
Context: 8K
Weights: Open

BaiduJun 30, 2025

ERNIE 4.5 (open models)

Baidu's first open-weight ERNIE release: ten models from 0.3B dense to 424B mixture-of-experts, including vision-language versions.

Type: Open-Weight
Context: 131K
Weights: Open

LG AI ResearchMar 18, 2025

EXAONE Deep

LG AI Research's reasoning models, built on EXAONE 3.5 and trained for step-by-step math, science and coding.

Type: Reasoning
Context: 33K
Weights: Open