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 |
upstage
|
|---|---|
| Company | upstage |
| Release Date | 2023-12-23 |
| Parameters (B) | 10.7 |
| Architecture | Depth Up-Scaled Transformer |
| Context Window | 4096 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 21.4 |
| Compute | Single GPU with 24GB VRAM for FP16 inference (e.g. RTX 3090/4090); ~7GB with Q4 quantization |
| Benchmark: ARC | 62.0 |
| Benchmark: GSM8K | 55.5 |
| Benchmark: HellaSwag | 84.6 |
| Benchmark: MMLU | 65.5 |
| Benchmark: TruthfulQA | 45.0 |
| Pricing (Input) | — |
| Pricing (Output) | — |