EXAONE 4 — local AI model by LG AI Research
Written by Jakub Rusinowski · Last updated
LG AI Research's EXAONE 4 line: EXAONE 4.0 (32B and 1.2B, July 2025) with a reasoning mode and a direct-answer mode, and EXAONE 4.5 (April 2026), LG's first open vision-language model. English, Korean and Spanish. Licensed for research and education only; commercial use needs a separate licence from LG.
Variants
The smallest EXAONE 4 variant needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| EXAONE 4.5 33B → 33B | ~20.8 GB | 262,144 | ollama run exaone-4 | |
| EXAONE 4.0 32B → 32B | ~20.1 GB | 131,072 | ollama run exaone-4 | |
| EXAONE 4.0 1.2B → 1.2B | ~1.6 GB | 65,536 | ollama run exaone-4 |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run EXAONE 4 locally
Install Ollama, then pull the tag.
ollama run exaone-4Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Research / non-commercial only — this licence does NOT permit shipping a commercial product.
Applies to: EXAONE 4.5 33B, EXAONE 4.0 32B, EXAONE 4.0 1.2BRecommended GPU
The cheapest catalogued GPU that runs EXAONE 4 locally (min 2 GB VRAM) is the Intel Arc B570 (10 GB).
EXAONE 4 — frequently asked questions
How much VRAM does EXAONE 4 need?
EXAONE 4 needs about 2 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: EXAONE 4.5 33B (21 GB, Q4_K_M); EXAONE 4.0 32B (20 GB, Q4_K_M); EXAONE 4.0 1.2B (2 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run EXAONE 4 on an RTX 4090 (24 GB)?
Yes — EXAONE 4 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for EXAONE 4?
Q4_K_M is the best balance of quality and VRAM for EXAONE 4 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run EXAONE 4 with Ollama?
EXAONE 4 has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.