LGAI-EXAONE models
1 LGAI-EXAONE model from LG AI Research on Hugging Face, from 237.1B to 237.1B parameters, published by LG AI Research in BF16, with a 256K-token context. The smallest official model, K-EXAONE-236B-A23B, needs about 530 GB of VRAM at its published precision; the cheapest live fit is AMD MI300X at $7.89/hr.
Pick a size
One row per official LGAI-EXAONE size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| K-EXAONE-236B-A23B | 237.1B | 530 GB | 265 GB | 132 GB | AMD MI300X × 3 | $7.89/hr | 1.5 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| K-EXAONE-236B-A23B | 237.1B | BF16 | 530 GB | AMD MI300X × 3 | $7.89/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. 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)
- EXAONE 4.0 (3 models)