EXAONE 4.0 models
3 EXAONE 4.0 models on Hugging Face, from 1.3B to 32.0B parameters. At the precision each one is published in, the smallest needs about 2.9 GB of VRAM (EXAONE-4.0-1.2B, cheapest live fit: RTX 5060 Ti) and the largest about 71.5 GB (EXAONE-4.0-32B, cheapest live fit: A100). The cheapest way to run EXAONE-4.0-1.2B is $0.110/hr.
EXAONE 4.0 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| EXAONE-4.0-1.2B | 1.3B | BF16 | 2.9 GB | RTX 5060 Ti | $0.110/hr |
| EXAONE-4.0-32B | 32.0B | BF16 | 71.5 GB | A100 | $1.31/hr |
| EXAONE-4.0-32B-FP8 | 32.0B | F8_E4M3 | 35.8 GB | RTX 4090 | $0.441/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from LG AI Research
- EXAONE 3.5 (4 models)
