Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Top downloads
Select 2-5 models
| Attribute |
LGAI-EXAONE
|
|---|---|
| Company | LGAI-EXAONE |
| Release Date | 2025-07-15 |
| Parameters (B) | 32 |
| Architecture | Transformer |
| Context Window | 131072 |
| Input Modalities | text |
| Open Source | Yes |
| License | other |
| Score | 8 |
| VRAM (GB) | 24 |
| Compute | 32B dense Transformer (~30.95B params excluding embeddings); ~66GB VRAM for BF16 inference, ~24GB with 4-bit quantization (AWQ/GPTQ/Q4_K_M); deployable via vLLM, TensorRT-LLM, or llama.cpp |
| Benchmark: AIME-2025 | 85.3 |
| Benchmark: GPQA-Diamond | 75.4 |
| Benchmark: IFEval | 83.7 |
| Benchmark: LiveCodeBench | 66.7 |
| Benchmark: MMLU-Pro | 81.8 |
| Pricing (Input) | — |
| Pricing (Output) | — |