Loading…
Loading…
Models / K-EXAONE-2.0
GPU memory needed (smallest version of each): K-EXAONE-2.0 750B about 1670.4 GB.
1 model (750B) · ↓ 3.5K downloads a month. 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/K-EXAONE-2.0-750B-A37B | vLLM | 1499 GB | 1670.4 GB | None big enough now |
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").