EXAONE Models — Hardware Requirements
3 EXAONE models from LGAI-EXAONE and the community, from the smallest that runs in 0.9 GB of VRAM up to 34.4B parameters. Every row links to full quantization tables and GPU compatibility.
All EXAONE Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| EXAONE 4.0 1.2B | 1.3B | 1.0 GB | 66K | ||
| EXAONE 3.5 2.4B Instruct | 2.4B | 0.9 GB | 33K | ||
| EXAONE 3.5 7.8B Instruct | 7.8B | 2.7 GB | 33K | ||
| EXAONE 3.0 7.8B Instruct | 7.8B | 17.2 GB | — | ||
| EXAONE 3.5 32B Instruct | 32.0B | 15.0 GB | 33K | ||
| EXAONE 4.5 33B | 34.4B | 15.4 GB | 262K |
Frequently Asked Questions
- How much VRAM do I need to run a EXAONE model?
- The smallest EXAONE model, EXAONE 3.5 2.4B Instruct, runs from 0.9 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which EXAONE models can I run on a 16 GB GPU?
- 5 of 6 EXAONE models fit in 16 GB of VRAM at some quantization, including EXAONE 3.5 7.8B Instruct, EXAONE 3.5 2.4B Instruct, EXAONE 4.5 33B.
- What is the most popular EXAONE model to run locally?
- EXAONE 3.5 7.8B Instruct is the most downloaded EXAONE model in local-friendly quantized formats. It runs from 2.7 GB of VRAM.