AxForge
Sign in Get started

Model reference · open weights

EXAONE-3.0

LLMs LGAI-EXAONE Text gen 1 build Its own licence terms 12k dl/mo

EXAONE-3.0 is an open-weight language model from LGAI-EXAONE. EXAONE-3.0-7.8B-Instruct (FP32) weighs 15.6 GB; the smallest configuration that runs it is RTX 4090 24 GB.

Request Rent a GPU

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

  • EXAONE-3.0-7.8B-Instruct is a bilingual generative model developed by LGAI-EXAONE for text generation tasks.
  • It features 7.8 billion parameters and supports English and Korean.
  • The model was pre-trained on 8 trillion curated tokens and post-trained using supervised fine-tuning and direct preference optimization.
  • It is distributed under the EXAONE AI Model License Agreement 1.1 - NC.

Summary of the LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct model card, 2026-10-01

Hugging Face ↗GitHub ↗Paper ↗

What it is

Released byLGAI-EXAONE
Released2024-07-31
Parameters7.8B
VRAM15.6 GB for the weights

What it runs on

Memory and cards for EXAONE-3.0-7.8B-Instruct (FP32)

15.6 GBweights, file size
762 MBruntime overhead, at least

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

CardWeights alone
RTX 3060 12 GB … RTX 4060 Ti 16 GB
2 smaller cards		does not fit
RTX 3090 24 GBfits
RTX 4090 24 GBfits
RTX 5090 32 GBfits
L40S 48 GBfits
A100 80 GBfits
H100 80 GBfits
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms