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 |
NousResearch
|
|---|---|
| Company | NousResearch |
| Release Date | 2024-01-17 |
| Parameters (B) | 10.7 |
| Architecture | Llama-based Transformer with YaRN RoPE scaling |
| Context Window | 32000 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 24 |
| Compute | Single NVIDIA GPU with 24GB+ VRAM (40GB recommended for full 32k context) |
| Benchmark: ARC | 59.6 |
| Benchmark: BBH | 49.7 |
| Benchmark: GPQA | 30.3 |
| Benchmark: GPQA-Diamond | 31.8 |
| Benchmark: HellaSwag | 83.7 |
| Benchmark: IFEval | 24.8 |
| Benchmark: MATH | 2.4 |
| Benchmark: MMLU | 64.4 |
| Benchmark: MMLU-Pro | 32.7 |
| Benchmark: TruthfulQA | 44.8 |
| Pricing (Input) | — |
| Pricing (Output) | — |