Loading…
Loading…
Models / EXAONE-4.0
2 models (1.2B to 32B) · ↓ 61.7K downloads a month · from $0.10/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalLGAI-EXAONE/EXAONE-4.0-1.2B | vLLM | 2.6 GB | 5.6 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalLGAI-EXAONE/EXAONE-4.0-32B | vLLM | 64 GB | 75.7 GB | $0.90/h 2x RTX A6000 |
| FP8LGAI-EXAONE/EXAONE-4.0-32B-FP8 | vLLM | 33 GB | 41.3 GB | $0.42/h 4x RTX 3060 |
| FP8 (furiosa-ai)furiosa-ai/EXAONE-4.0-32B-FP8 | vLLM | 33 GB | 41.3 GB | $0.42/h 4x RTX 3060 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").