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 | 2024-12-09 |
| Parameters (B) | 32 |
| Architecture | Transformer |
| Context Window | 32768 |
| Input Modalities | text |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 20 |
| Compute | Single NVIDIA GPU with ≥20 GB VRAM (e.g. RTX 3090/4090, A10); AWQ W4A16g128 weight-only quantization with bfloat16 activations; requires transformers≥4.43 and autoawq≥0.2.7.post3; supports vLLM, TensorRT-LLM, SGLang, llama.cpp, and Ollama |
| Benchmark: ARC | 91.7 |
| Benchmark: BBH | 75.3 |
| Benchmark: GPQA | 39.7 |
| Benchmark: GSM8K | 91.9 |
| Benchmark: HumanEval | 87.2 |
| Benchmark: IFEval | 81.7 |
| Benchmark: MATH | 70.5 |
| Benchmark: MBPP | 81.8 |
| Benchmark: MMLU | 78.3 |
| Pricing (Input) | — |
| Pricing (Output) | — |