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 |
deepseek-ai
|
|---|---|
| Company | deepseek-ai |
| Release Date | 2023-11-29 |
| Parameters (B) | 7 |
| Architecture | Transformer |
| Context Window | 4096 |
| Input Modalities | text |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 16 |
| Compute | Single NVIDIA GPU with 16GB+ VRAM (e.g. RTX 4090, A10, or A100 40GB) for BF16/FP16 inference |
| Benchmark: AGIEval | 26.4 |
| Benchmark: ARC | 48.1 |
| Benchmark: BBH | 39.5 |
| Benchmark: C-Eval | 45 |
| Benchmark: DROP | 41 |
| Benchmark: GSM8K | 17.4 |
| Benchmark: HellaSwag | 75.4 |
| Benchmark: HumanEval | 26.2 |
| Benchmark: MATH | 6 |
| Benchmark: MBPP | 39 |
| Benchmark: MMLU | 48.2 |
| Pricing (Input) | — |
| Pricing (Output) | — |