llmrun

EXAONE Models — Hardware Requirements

4 EXAONE models from LGAI-EXAONE and the community, from the smallest that runs in 2.1 GB of VRAM at Q4 up to 34.4B parameters. Every row links to full quantization tables and GPU compatibility.

All EXAONE Models by Size

ModelParamsContext
EXAONE 4.0 1.2B1.3B66K
EXAONE 3.5 2.4B Instruct2.4B33K
EXAONE 3.5 7.8B Instruct7.8B33K
EXAONE 3.0 7.8B Instruct7.8B—
EXAONE 3.5 32B Instruct32.0B33K
EXAONE 4.5 33B34.4B262K

Frequently Asked Questions

How much VRAM do I need to run a EXAONE model?
The smallest EXAONE model, EXAONE 4.0 1.2B, runs from 2.1 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 1.0 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
Which EXAONE models can I run on a 16 GB GPU?
4 of 6 EXAONE models fit in 16 GB of VRAM at Q4_K_M, including EXAONE 3.5 7.8B Instruct, EXAONE 3.5 2.4B Instruct, EXAONE 4.0 1.2B.
What is the most popular EXAONE model to run locally?
EXAONE 3.5 32B Instruct is the most downloaded EXAONE model in local-friendly quantized formats. It runs from 24.9 GB of VRAM at Q4_K_M.